© 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. 20-GEMMASCOPE-RES-131K
    6. 112394
    Prev
    Next
    INDEX
    Explanations

    terms related to tuning and adjustments

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

    tuning and adjustment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.57
     femelle
    -0.45
     mâle
    -0.45
     moitié
    -0.43
    gemeins
    -0.43
     bancaire
    -0.42
     Herrick
    -0.41
     fausse
    -0.41
    CompanyId
    -0.41
    bės
    -0.41
    POSITIVE LOGITS
     Tune
    1.09
     tune
    1.05
     tuning
    1.04
    Tune
    1.02
     tuned
    1.01
    tune
    0.98
     Tuning
    0.92
     Tunes
    0.91
    tuning
    0.91
     tunes
    0.90
    Activations Density 0.008%

    No Known Activations