© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63704
    Prev
    Next
    INDEX
    Explanations

    descriptive terms indicating exceptional quality or performance

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

    amazing and positive adjectives

    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
    DockStyle
    -0.56
    </tfoot>
    -0.45
    glBindBuffer
    -0.45
    -------
    -0.45
    DCE
    -0.44
     insuffisamment
    -0.44
     trö
    -0.43
    덜
    -0.43
    KYO
    -0.43
     hodiny
    -0.43
    POSITIVE LOGITS
    amazing
    1.06
     Amazing
    1.05
    Amazing
    1.02
     amazing
    0.93
     AMAZING
    0.89
    AMAZING
    0.82
    mazing
    0.82
     Great
    0.74
    wonderful
    0.74
     Fantastic
    0.71
    Activations Density 0.004%

    No Known Activations