© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14694
    Prev
    Next
    INDEX
    Explanations

    functional and practical connections in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    enablement or assistance

    np_acts-logits-general · gemini-2.0-flash

    enables or links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.48
    ,:);
    -0.40
    ")}
    -0.39
    addCriterion
    -0.37
     spend
    -0.36
    BindView
    -0.35
     jPanel
    -0.35
     хвата
    -0.33
    IBOutlet
    -0.33
     nonatomic
    -0.33
    POSITIVE LOGITS
     enables
    1.25
     allows
    1.21
     provides
    1.08
     helps
    1.04
     umožňuje
    1.02
     gives
    1.01
     prevents
    0.99
    provides
    0.97
     ensures
    0.95
     memungkinkan
    0.94
    Activations Density 0.637%

    No Known Activations