© 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. 1107
    Prev
    Next
    INDEX
    Explanations

    terms related to the evaluation and status of scientific testing and results

    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
     InputDecoration
    -0.47
     jspb
    -0.47
    المناصب
    -0.47
    ecia
    -0.45
    */].
    -0.44
    бір
    -0.43
     gbc
    -0.42
     tratta
    -0.42
    السكان
    -0.42
     aprovechar
    -0.41
    POSITIVE LOGITS
     مشين
    0.74
     ویکی‌پدیای
    0.70
    ConstraintMaker
    0.69
    Tembelea
    0.68
     Infórmanos
    0.64
     CreateTagHelper
    0.64
    findpost
    0.62
    IntoConstraints
    0.61
    abestanden
    0.61
    LayoutConstraint
    0.60
    Activations Density 1.570%

    No Known Activations