© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1618
    Prev
    Next
    INDEX
    Explanations

    legal citations and references to statutes or legal procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.79
    SOUNDBITE
    -0.78
     itſelf
    -0.74
     houſe
    -0.73
     Grimal
    -0.71
     fubject
    -0.70
    itsub
    -0.69
     Menon
    -0.69
     Curran
    -0.69
     purpoſe
    -0.68
    POSITIVE LOGITS
     kaynağından
    0.73
     NSCoder
    0.59
    ↵↵
    0.56
    SuppressLint
    0.52
    PrototypeOf
    0.50
    thâu
    0.47
    nextDouble
    0.47
    ⓧ
    0.46
    ↵↵↵↵
    0.46
    eraard
    0.46
    Activations Density 0.742%

    No Known Activations