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

    Neuronpedia

    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. 9-GEMMASCOPE-RES-131K
    11. 84526
    Prev
    Next
    INDEX
    Explanations

    occurrences of indexing or identification elements in arrays or datasets

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

    idx or index identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ering
    -0.50
    General
    -0.47
    <b>
    -0.44
    Chham
    -0.43
    UserScript
    -0.42
    <i>
    -0.42
    using
    -0.40
    Heinrich
    -0.39
    Bell
    -0.39
    language
    -0.39
    POSITIVE LOGITS
    idx
    2.20
     idx
    2.05
    Idx
    1.77
    IDX
    1.49
    idxs
    1.23
     Indices
    0.83
     indices
    0.78
    dix
    0.78
    indx
    0.70
    idex
    0.68
    Activations Density 0.060%

    No Known Activations