© 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. 6821
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their associated roles or titles

    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
    \{\\
    -0.61
    IsMutable
    -0.48
     autorytatywna
    -0.47
     Wicidata
    -0.45
    OCCURRED
    -0.43
    wości
    -0.42
     '\\;'
    -0.40
    ArrowToggle
    -0.38
    cyd
    -0.38
    Становништво
    -0.37
    POSITIVE LOGITS
     bearing
    2.14
     bears
    1.98
     bear
    1.96
     Bearing
    1.72
    bearing
    1.69
    Bearing
    1.65
    bear
    1.57
    bears
    1.55
     BEAR
    1.54
    Bear
    1.49
    Activations Density 0.585%

    No Known Activations