© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    conversational elements and personal reflections

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

    contrast and auxiliary verbs

    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
     even
    -0.82
    even
    -0.73
     навіть
    -0.71
     даже
    -0.69
     nawet
    -0.67
     Even
    -0.66
    Even
    -0.64
     EVEN
    -0.63
     حتی
    -0.62
    Даже
    -0.61
    POSITIVE LOGITS
     nonetheless
    1.00
     зато
    0.99
     nevertheless
    0.98
    却是
    0.77
    却
    0.76
    卻
    0.74
    Nevertheless
    0.69
     comunque
    0.67
     néanmoins
    0.66
    Nonetheless
    0.66
    Activations Density 0.131%

    No Known Activations