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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6204
    Prev
    Next
    INDEX
    Explanations

    dialogues or conversations with structural indicators such as quotations and turns of speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.51
    intios
    -0.44
    shadowOffset
    -0.44
    mä
    -0.42
    MessageOf
    -0.42
     Wartawan
    -0.42
    mstyle
    -0.41
     heaviest
    -0.41
    kloped
    -0.41
    Streamer
    -0.40
    POSITIVE LOGITS
    ersdorf
    0.63
     الحره
    0.61
     annat
    0.60
    ymce
    0.59
     nahilalakip
    0.59
    UnusedPrivate
    0.58
    JspWriter
    0.57
     BorderRadius
    0.56
     berarti
    0.56
    مصادر
    0.56
    Activations Density 0.137%

    No Known Activations