© 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. 10389
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their affiliations or titles

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

    punctuation and structural elements

    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
    niſſe
    -0.86
    ſſung
    -0.84
    RegressionTest
    -0.83
     imagui
    -0.82
     ſind
    -0.82
    abestanden
    -0.81
     fashiola
    -0.79
     disambiguazione
    -0.78
    <unused20>
    -0.77
    [@BOS@]
    -0.77
    POSITIVE LOGITS
    the
    0.61
     the
    0.60
     our
    0.58
     selaku
    0.46
    our
    0.36
     who
    0.35
     your
    0.32
     their
    0.32
    min
    0.30
    ti
    0.30
    Activations Density 0.088%

    No Known Activations