© 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. 9-GEMMASCOPE-RES-16K
    6. 9475
    Prev
    Next
    INDEX
    Explanations

    references to various inventions and technologies

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

    the beginning of encyclopedia or factual entries about inventions, products, or technical concepts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.53
     nahilalakip
    -0.45
    êmio
    -0.40
    äsident
    -0.39
    onCreate
    -0.37
    ?,?,
    -0.36
    ToBounds
    -0.36
     مواليد
    -0.35
    اص
    -0.35
    AMAHA
    -0.35
    POSITIVE LOGITS
    UrlResolution
    0.46
    يميديا
    0.43
    awtextra
    0.42
    openzeppelin
    0.42
    LookAnd
    0.41
    IZO
    0.40
     TType
    0.40
     debole
    0.40
    stuff
    0.40
    tvguidetime
    0.40
    Activations Density 1.076%

    No Known Activations