© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81545
    Prev
    Next
    INDEX
    Explanations

    references to knobs and user interface elements, particularly related to "gnome."

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

    knob, knobs, snob, gnome, Knoll

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ۪
    -0.54
    MPI
    -0.48
    Ì
    -0.47
    `;
    -0.45
    '));
    -0.44
     Beatrice
    -0.44
    ()));
    -0.43
    I
    -0.43
     MPI
    -0.42
     adult
    -0.42
    POSITIVE LOGITS
     knob
    1.98
    knob
    1.88
     Knob
    1.78
     knobs
    1.77
     Kno
    1.13
    Kno
    1.12
    kno
    1.06
    nob
    1.04
     kno
    0.96
     knop
    0.90
    Activations Density 0.004%

    No Known Activations