© 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. 0-GEMMASCOPE-RES-16K
    6. 9319
    Prev
    Next
    INDEX
    Explanations

    statements of agreement or consensus between opinions

    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
    叶凌天
    -0.47
    thenes
    -0.47
     OPPO
    -0.46
    ↹
    -0.46
    createObject
    -0.45
     ​​
    -0.44
    cornerRadius
    -0.43
    slidesToShow
    -0.43
     useRouter
    -0.43
     Inscription
    -0.43
    POSITIVE LOGITS
     agree
    0.90
    Agree
    0.86
     agreement
    0.83
     Agree
    0.81
     agreeing
    0.75
     agrees
    0.72
    agree
    0.71
    Agreed
    0.70
     terms
    0.68
     agreed
    0.66
    Activations Density 0.251%

    No Known Activations