© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7301
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue from individuals

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

    Text after quotation marks

    np_acts-logits-general · gemini-2.0-flash

    start of quotes

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    WireFormatLite
    -0.48
    rungsseite
    -0.46
    NUMX
    -0.45
    awaiter
    -0.42
    DoubleQuotes
    -0.42
     مشين
    -0.41
    enseignements
    -0.40
     doigts
    -0.39
    Enllaces
    -0.39
    ollary
    -0.39
    POSITIVE LOGITS
    makeText
    0.51
    setDo
    0.47
    ChrTalk
    0.47
    MessageOf
    0.43
    complexType
    0.42
     виправивши
    0.41
    awtextra
    0.41
    BindView
    0.40
    addCriterion
    0.40
    “
    0.40
    Activations Density 0.088%

    No Known Activations