© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85088
    Prev
    Next
    INDEX
    Explanations

    punctuation and structure within sentences, particularly focusing on periods and specific types of separators

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

    words starting with un

    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
    Personendaten
    -0.86
     ModelExpression
    -0.85
    MigrationBuilder
    -0.80
     propOrder
    -0.79
     صوتيه
    -0.78
    parsedMessage
    -0.75
    webElementGuid
    -0.73
    httphttps
    -0.71
    contentLoaded
    -0.70
    MessageOf
    -0.70
    POSITIVE LOGITS
     Un
    1.16
     un
    1.10
    Un
    1.07
     Uns
    0.95
     uns
    0.86
    Uns
    0.85
     Und
    0.85
    un
    0.84
     uncon
    0.78
     UN
    0.76
    Activations Density 0.112%

    No Known Activations