Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 30821
    Prev
    Next
    INDEX
    Explanations

    programming-related error messages and conditions pertaining to null or empty values

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

    checks for null or missing

    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
    repaint
    -0.39
    delwed
    -0.35
    WithMany
    -0.35
    ToMany
    -0.35
    +:+
    -0.34
    toHave
    -0.34
     ListTile
    -0.34
    ReusableCell
    -0.34
     Specialists
    -0.33
     Werth
    -0.33
    POSITIVE LOGITS
     nahilalakip
    0.74
    WebElementEntity
    0.59
    NullException
    0.57
    IntoConstraints
    0.51
    ftagPool
    0.50
     missing
    0.49
    UnusedPrivate
    0.48
     nedost
    0.47
     lack
    0.47
     Lack
    0.47
    Activations Density 0.017%

    No Known Activations