© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38424
    Prev
    Next
    INDEX
    Explanations

    descriptive qualities related to sound and taste sensations

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

    cool, sharper, or snippy

    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
    inheritDoc
    -0.34
     hope
    -0.34
    PART
    -0.33
    sschutz
    -0.32
     mass
    -0.30
    postIndex
    -0.29
     guilt
    -0.29
    hskip
    -0.28
    inigte
    -0.28
    bcm
    -0.28
    POSITIVE LOGITS
     brisk
    0.89
     briskly
    0.80
     crisp
    0.78
     Crisp
    0.77
    :✨
    0.76
     freshen
    0.68
     Stiff
    0.66
    __(/*!
    0.65
     pinulongan
    0.64
     sharper
    0.62
    Activations Density 0.058%

    No Known Activations