Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5731
    Prev
    Next
    INDEX
    Explanations

    bullet points and structured list elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.68
    Tikang
    -0.60
    IntoConstraints
    -0.52
    jspx
    -0.50
     
    -0.48
    BoxLayout
    -0.47
     Italijani
    -0.46
    Erreferentziak
    -0.45
    divarius
    -0.43
    iotensin
    -0.43
    POSITIVE LOGITS
     •
    0.81
    •
    0.78
    ••
    0.73
    InjectAttribute
    0.67
    .•
    0.66
    ••••
    0.63
    cdot
    0.62
    *
    0.62
    •••
    0.60
    )•
    0.60
    Activations Density 0.146%

    No Known Activations