© 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. 20-GEMMASCOPE-RES-131K
    11. 16368
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "pre" in various contexts

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

    prefix "pre"

    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
    bootstrapcdn
    -0.67
    ScopeManager
    -0.62
     HasFactory
    -0.56
     userModel
    -0.54
    存于互联网档案馆
    -0.53
    yntaxException
    -0.53
    ฉัน
    -0.52
    Figura
    -0.52
    TokenNameLPAREN
    -0.50
    AndView
    -0.50
    POSITIVE LOGITS
     pre
    1.16
     Pre
    1.07
    Pre
    1.02
     PRE
    0.97
    pre
    0.95
    PRE
    0.93
     pré
    0.85
     before
    0.72
     Pré
    0.70
    before
    0.69
    Activations Density 0.026%

    No Known Activations