© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8137
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

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

    Two- or three-letter abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Shonda Rhimes, Veronika Hug

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    featureID
    -0.84
    AndEndTag
    -0.77
    parsedMessage
    -0.68
    دانشنامهٔ
    -0.66
    󠁴
    -0.63
    GenerationType
    -0.63
    <unused14>
    -0.62
    [@BOS@]
    -0.62
    <unused3>
    -0.62
    <unused28>
    -0.62
    POSITIVE LOGITS
     Ar
    0.52
     Mat
    0.48
     Mar
    0.46
     Kar
    0.46
     Ti
    0.45
     Nan
    0.44
     Se
    0.44
     Ma
    0.44
     Sil
    0.43
     Sp
    0.43
    Activations Density 2.212%

    No Known Activations