© 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. 31-GEMMASCOPE-RES-131K
    11. 24506
    Prev
    Next
    INDEX
    Explanations

    specific phrases or patterns involving sentence structure and punctuation

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

    contrast and concession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.85
     dieſes
    -0.66
     myſelf
    -0.66
     surla
    -0.64
    出版年
    -0.63
     dieſer
    -0.62
     dieſen
    -0.62
    ſelf
    -0.62
     تضيفلها
    -0.61
     виправивши
    -0.61
    POSITIVE LOGITS
     çoğu
    0.47
    Though
    0.46
    Unlike
    0.46
    Although
    0.46
    astéroïdes
    0.45
    由於
    0.44
     mivel
    0.44
    Contrary
    0.44
     Contrary
    0.43
    Most
    0.42
    Activations Density 0.125%

    No Known Activations