© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 61982
    Prev
    Next
    INDEX
    Explanations

    the specific article "the."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the value or term

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly detects the start-of-sequence (beginning-of-text) token.

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    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
    Negative Logits
     irse
    -0.38
     Sehingga
    -0.37
     république
    -0.37
     кӀ
    -0.36
     hodiny
    -0.36
    rungsseite
    -0.36
    føl
    -0.35
     eenige
    -0.35
    følge
    -0.35
     coroa
    -0.35
    POSITIVE LOGITS
     itſelf
    0.64
    glEnd
    0.58
     IllegalArgument
    0.58
     the
    0.58
    cane
    0.54
     destructor
    0.54
    这一幕
    0.54
     newName
    0.52
    jsonwebtoken
    0.52
    <start_of_turn>
    0.52
    Activations Density 0.001%

    No Known Activations