© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6698
    Prev
    Next
    INDEX
    Explanations

    structured data related to sports events and outcomes

    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
    contentLoaded
    -0.47
    цездатний
    -0.44
    PreInfinity
    -0.42
     Administrativna
    -0.42
    RenderAtEndOf
    -0.40
     Reverso
    -0.38
    SharedCtor
    -0.38
    Hentet
    -0.37
     sendi
    -0.37
    بوابة
    -0.36
    POSITIVE LOGITS
     hotly
    0.77
     contest
    0.76
     intense
    0.76
     riveting
    0.75
     exciting
    0.75
     thrilling
    0.74
     battle
    0.73
     heated
    0.71
     deciding
    0.71
     suspense
    0.71
    Activations Density 0.277%

    No Known Activations