© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10235
    Prev
    Next
    INDEX
    Explanations

    concepts related to magnetic properties and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific or technical terms related to material properties in physics and engineering contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical physics/engineering passages describing material properties and parameters, often with Greek symbols, units, and equation-style notation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical and scientific terms related to material properties, particularly density, permeability, and modulus in physics and engineering contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.54
    WebElementEntity
    -0.48
    GIVEREF
    -0.46
     épar
    -0.44
     étoit
    -0.42
     Elabor
    -0.41
     reca
    -0.41
     breech
    -0.41
    PageRoute
    -0.41
    ValueStyle
    -0.41
    POSITIVE LOGITS
     vlastnosti
    0.49
     egenskaper
    0.47
     materials
    0.46
     anisotropic
    0.45
     properties
    0.45
     Eigenschaften
    0.44
     propriedades
    0.44
     propiedades
    0.44
     ujednoznacz
    0.41
     anisotropy
    0.41
    Activations Density 0.607%

    No Known Activations