© 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. 3056
    Prev
    Next
    INDEX
    Explanations

    terminology related to functionality in various contexts

    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
    enderror
    -0.35
    󠁢
    -0.35
    UrlResolution
    -0.34
    findpost
    -0.34
    Personendaten
    -0.33
     mergeFrom
    -0.32
    StoreMessageInfo
    -0.32
     cried
    -0.31
    },{
    -0.31
    )$_
    -0.30
    POSITIVE LOGITS
     FUNCTION
    2.98
     functional
    2.97
     Function
    2.95
     func
    2.94
     function
    2.86
     funk
    2.81
     fonction
    2.77
     Functional
    2.75
    FUNCTION
    2.75
    Function
    2.70
    Activations Density 0.210%

    No Known Activations