© 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. 0-GEMMASCOPE-RES-16K
    11. 9858
    Prev
    Next
    INDEX
    Explanations

    specific words and abbreviations, primarily related to terminology and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Se
    -0.54
     ST
    -0.54
     SE
    -0.47
     σ
    -0.47
     Si
    -0.47
     St
    -0.45
     se
    -0.44
     Σ
    -0.44
    Flammability
    -0.44
     Sta
    -0.43
    POSITIVE LOGITS
    sex
    1.16
    so
    1.10
    sem
    1.07
    sto
    1.01
    sed
    1.00
    sets
    1.00
    see
    1.00
    ser
    0.99
    simp
    0.97
    site
    0.96
    Activations Density 1.227%

    No Known Activations