© 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. 128721
    Prev
    Next
    INDEX
    Explanations

    references to groups of animals, specifically herds

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

    herd or flock

    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
    Negative Logits
    /*
    -0.49
     Philips
    -0.46
    endcsname
    -0.45
     Az
    -0.45
     sigui
    -0.43
     sin
    -0.42
     Pos
    -0.42
     Pap
    -0.42
     paper
    -0.42
     Nobel
    -0.41
    POSITIVE LOGITS
     herd
    2.13
     Herd
    1.93
    herd
    1.84
     herds
    1.72
    erd
    0.93
     Flock
    0.81
     troup
    0.77
    heard
    0.76
    flock
    0.75
     flock
    0.74
    Activations Density 0.002%

    No Known Activations