© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 95549
    Prev
    Next
    INDEX
    Explanations

    programming and coding-related syntax and structures

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

    Greek letters and punctuation in expressions

    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
    ValueStyle
    -0.93
     otomatig
    -0.89
     незавершена
    -0.83
     transférez
    -0.82
     فريبيس
    -0.81
     queſta
    -0.81
    EndContext
    -0.77
    iſche
    -0.76
    PreferredItem
    -0.76
    <unused52>
    -0.75
    POSITIVE LOGITS
     therefore
    0.36
     win
    0.35
     further
    0.34
     also
    0.33
     compound
    0.33
    on
    0.32
    Z
    0.32
     sequence
    0.32
     through
    0.31
    seq
    0.31
    Activations Density 0.042%

    No Known Activations