© 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 EvalsExportsinterp-engineNEWAPI 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. 35587
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural indicators within the text

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

    song structure (chorus, verse, bridge)

    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
    tagHelperRunner
    -0.82
     صوتيه
    -0.69
    GraphicsUnit
    -0.66
    Datuak
    -0.66
     informée
    -0.61
    DoubleQuotes
    -0.58
    principalTable
    -0.57
    awtextra
    -0.57
    expandindo
    -0.56
    StreetMap
    -0.56
    POSITIVE LOGITS
     chorus
    1.37
    Chorus
    1.16
     verse
    1.14
     Chorus
    1.08
    chorus
    1.05
     verses
    0.99
     Verse
    0.98
    CHORUS
    0.88
     CHORUS
    0.88
    Verse
    0.87
    Activations Density 0.058%

    No Known Activations