© 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. 31-GEMMASCOPE-RES-16K
    11. 2837
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to definitions and meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing enumeration or listing of multiple items or actions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    どの
    -0.37
    zzard
    -0.29
    ど
    -0.28
     каком
    -0.25
     ど
    -0.24
     spie
    -0.24
    šní
    -0.24
    ImageLoader
    -0.23
    deki
    -0.22
    ýchod
    -0.22
    POSITIVE LOGITS
     thing
    2.83
     something
    2.70
     things
    2.58
    something
    2.34
    Something
    2.28
     Something
    2.28
    thing
    2.25
     coisa
    2.22
     Things
    2.17
    things
    2.14
    Activations Density 0.895%

    No Known Activations