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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11790
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')")
    -0.33
     незавершена
    -0.32
     suspensão
    -0.30
    例文帳に追加
    -0.30
     rõ
    -0.30
     meia
    -0.30
     borboleta
    -0.29
     Erscheinung
    -0.29
    ’
    -0.29
     stanu
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.82
    adaptiveStyles
    0.68
     queſta
    0.67
    MemoryWarning
    0.63
    createCanvas
    0.62
    NUMX
    0.59
     RIPRODUZIONE
    0.58
     esternos
    0.58
    GEBURTS
    0.57
    yntaxException
    0.57
    Activations Density 0.510%

    No Known Activations