© 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. 7-GEMMASCOPE-RES-16K
    11. 15243
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of the concept of "usage" or "activity" in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTCF
    -0.39
    egen
    -0.34
     brought
    -0.33
     FLA
    -0.32
     Balo
    -0.32
    mogorov
    -0.32
    водитель
    -0.31
     knocked
    -0.31
    gelopen
    -0.30
     mxArray
    -0.30
    POSITIVE LOGITS
     frequent
    0.97
    Frequent
    0.96
    frequent
    0.96
     Frequent
    0.91
     frequently
    0.85
    頻繁
    0.80
    频繁
    0.78
    frequently
    0.77
     frequ
    0.74
     čast
    0.74
    Activations Density 0.397%

    No Known Activations