© 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. 6789
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly those associated with layouts and data mapping

    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
     houſe
    -0.75
     يتيمه
    -0.73
    tonsoft
    -0.73
    parsedMessage
    -0.73
     pleaſure
    -0.70
     autorytatywna
    -0.69
     contextLoads
    -0.68
    hoeddwyd
    -0.68
    出版年
    -0.67
    expandindo
    -0.67
    POSITIVE LOGITS
     without
    0.58
    without
    0.53
    Without
    0.52
     Without
    0.50
    raw
    0.47
     before
    0.47
    Raw
    0.43
    With
    0.43
     без
    0.43
    For
    0.42
    Activations Density 0.814%

    No Known Activations