© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1058
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, particularly focusing on function definitions and module patterns in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    </strong>
    -0.48
    </em>
    -0.46
     I
    -0.43
     (
    -0.43
    I
    -0.43
    """
    -0.43
    .
    -0.42
     BoxDecoration
    -0.42
    จัก
    -0.41
    mal
    -0.40
    POSITIVE LOGITS
    abetes
    0.90
    InjectAttribute
    0.84
    例文帳に追加
    0.79
    ]--;
    0.78
    parsedMessage
    0.77
     >=",
    0.76
    ècie
    0.76
    MessageOf
    0.75
    ItemBackground
    0.75
    Espèce
    0.74
    Activations Density 0.100%

    No Known Activations