© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 59384
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "sc" and its variations, which likely relate to "scene" or "scorpion" in context

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

    "sc" prefix

    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
    itism
    -0.52
    Datuak
    -0.51
    ujte
    -0.50
     Pax
    -0.50
     Zimmerman
    -0.50
    ayer
    -0.49
    ize
    -0.49
    hax
    -0.48
    imax
    -0.48
    ganos
    -0.47
    POSITIVE LOGITS
    sc
    0.91
    Sc
    0.85
    SC
    0.85
     sc
    0.85
     SC
    0.83
     Sc
    0.83
    SSC
    0.63
    Scy
    0.63
     Scully
    0.62
     SCD
    0.62
    Activations Density 0.026%

    No Known Activations