© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 993
    Prev
    Next
    INDEX
    Explanations

    instances of the term "cap" and its variations in different contexts

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

    "cap" or capitalization

    np_acts-logits-general · gemini-2.0-flash

    cap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    world
    -0.45
    WORLD
    -0.44
     world
    -0.42
    AnimationsModule
    -0.42
     sû
    -0.40
    NESDAY
    -0.39
     Rou
    -0.39
    rician
    -0.39
    スメ
    -0.38
    World
    -0.38
    POSITIVE LOGITS
     cap
    2.23
     Cap
    2.09
    Cap
    2.05
    cap
    2.03
     caps
    1.77
     CAP
    1.77
    CAP
    1.70
     Caps
    1.69
    caps
    1.57
    Caps
    1.49
    Activations Density 0.199%

    No Known Activations