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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8978
    Prev
    Next
    INDEX
    Explanations

    terms related to physical properties and behaviors of materials in a scientific context

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

    technical or scientific terms related to physical structures, components, or spatial arrangements, particularly in materials science, physics, and engineering contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    specialized scientific/engineering terminology that names physical structures, components, or phenomena.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.72
     kaarangay
    -0.61
     cherchés
    -0.57
    RenderAtEndOf
    -0.56
     EClass
    -0.53
    UserScript
    -0.52
    tableFuture
    -0.50
     Standardization
    -0.48
     standardization
    -0.48
     Extrem
    -0.48
    POSITIVE LOGITS
    GenerationType
    0.41
     importado
    0.39
     kanssa
    0.39
    NVIC
    0.38
     kapturem
    0.38
     franquicia
    0.36
     judiciales
    0.36
     tangki
    0.36
    audiovisuel
    0.36
     imediatamente
    0.35
    Activations Density 1.780%

    No Known Activations