© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 50331
    Prev
    Next
    INDEX
    Explanations

    references to examples and sample code in a programming context

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

    samples and demos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ModelExpression
    -0.42
     invokingState
    -0.41
    makeConstraints
    -0.41
    aarrggbb
    -0.39
    FunctionFlags
    -0.39
    onomía
    -0.38
    GEBURTS
    -0.38
     跳转至
    -0.37
    LayoutConstraint
    -0.36
    InitVars
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.69
     autorytatywna
    0.48
     Demo
    0.45
    DEMO
    0.44
     demo
    0.43
    Demo
    0.42
    MENAFN
    0.42
     setContent
    0.41
     demonstr
    0.41
    demo
    0.41
    Activations Density 0.262%

    No Known Activations