© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14477
    Prev
    Next
    INDEX
    Explanations

    patterns related to structured data or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.51
     BoxFit
    -0.50
    matchCondition
    -0.45
     onBind
    -0.44
    AutoScale
    -0.43
    +#+#
    -0.43
    ExtendWith
    -0.42
     chapéu
    -0.42
    bootstrapcdn
    -0.42
    Tembelea
    -0.42
    POSITIVE LOGITS
     ord
    0.50
    Autoritní
    0.46
    省市镇
    0.42
    >";
    0.42
    korb
    0.41
     ASCII
    0.41
    raszamy
    0.41
    Portail
    0.41
    ord
    0.41
     resourceCulture
    0.39
    Activations Density 0.654%

    No Known Activations