© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 30100
    Prev
    Next
    INDEX
    Explanations

    references to specific minerals, allergies, product types, and quality descriptors related to various materials or processes

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

    types of data storage and interfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     nakalista
    -0.74
     pinulongan
    -0.63
     bezeichneter
    -0.55
    interopRequire
    -0.52
     ErrIntOverflow
    -0.50
    Hozzáférés
    -0.49
     تضيفلها
    -0.48
    MemoryWarning
    -0.48
     kasarigan
    -0.45
     Infórmanos
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.56
    ,
    0.46
    TypedDataSet
    0.44
    ModelSerializer
    0.44
     and
    0.43
    WithIOException
    0.42
     gantung
    0.40
     Negra
    0.39
    richTextPanel
    0.39
     gömlek
    0.38
    Activations Density 0.047%

    No Known Activations