© 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. 99674
    Prev
    Next
    INDEX
    Explanations

    references to letters and their usage in various contexts

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

    letters and alphabets

    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
     increí
    -0.58
     pérd
    -0.52
     față
    -0.47
     termica
    -0.46
     potenciales
    -0.45
     preventivo
    -0.45
     hidráulica
    -0.45
     spreken
    -0.45
     bestaande
    -0.44
     indígen
    -0.43
    POSITIVE LOGITS
    Alphabet
    0.87
    fromCharCode
    0.85
    alphabet
    0.84
     letters
    0.82
     alphabet
    0.80
     Alphabet
    0.79
    letters
    0.78
     letter
    0.76
     LETTER
    0.73
     alphabets
    0.73
    Activations Density 0.015%

    No Known Activations