© 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. 7117
    Prev
    Next
    INDEX
    Explanations

    semicolons, parentheses, and other punctuation and formatting symbols common in programming code

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

    Code syntax or special characters

    np_acts-logits-general · gemini-2.0-flash

    code structure and delimiters

    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
    kof
    -0.47
    RenderAtEndOf
    -0.45
     Gae
    -0.45
    حات
    -0.43
    MessageOf
    -0.42
    restle
    -0.42
    gister
    -0.42
    inoma
    -0.42
     Exhibit
    -0.41
     Movie
    -0.40
    POSITIVE LOGITS
    pushFollow
    0.60
    MultipartFile
    0.50
    makeConstraints
    0.47
    󠁴
    0.45
     getItemId
    0.43
     emailAlready
    0.42
    InjectAttribute
    0.42
    󠁣
    0.41
    ConfigureAwait
    0.40
    parsedMessage
    0.40
    Activations Density 0.616%

    No Known Activations