© 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. 64548
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in a text

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

    click or Description

    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
    <eos>
    -1.61
    }$.\\
    -0.86
    ↵↵↵↵↵↵↵
    -0.80
    ↵↵↵↵↵↵↵↵
    -0.77
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.75
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.75
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.75
    $.\\
    -0.75
    ↵↵↵↵↵↵↵↵↵↵
    -0.75
    POSITIVE LOGITS
     Мексичка
    0.54
     ویکی‌پدی
    0.53
     MenuView
    0.50
    RenderAtEndOf
    0.47
    fjspx
    0.47
    цездатний
    0.47
     Савезне
    0.47
    исленность
    0.43
    UrlResolution
    0.41
     '\\;'
    0.40
    Activations Density 0.055%

    No Known Activations