© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 7290
    Prev
    Next
    INDEX
    Explanations

    instances of commands or instructions involving actions or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.68
    hdashline
    -0.60
    unehmen
    -0.60
     typelib
    -0.55
    "]();
    -0.55
    "]);
    -0.55
    "}},
    -0.54
     Ouverture
    -0.54
     exported
    -0.53
    ']));
    -0.52
    POSITIVE LOGITS
    principalColumn
    0.70
    LEn
    0.60
    objc
    0.59
    waitKey
    0.58
     IBOutlet
    0.57
    componentDid
    0.55
    IComponent
    0.55
    SystemColors
    0.53
    componentWill
    0.53
    Eloquent
    0.52
    Activations Density 0.179%

    No Known Activations