© 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. 13729
    Prev
    Next
    INDEX
    Explanations

    references to dog breeds and related terminology

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

    hound, collie, Greyhound

    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
     estekak
    -0.45
    })`
    -0.40
    NotExist
    -0.37
    جمعیت
    -0.36
    Gustav
    -0.35
     Saito
    -0.35
    RISE
    -0.35
    ∊
    -0.35
    )++;
    -0.35
     وز
    -0.35
    POSITIVE LOGITS
    hound
    2.52
     Hound
    2.17
     hound
    2.03
    Hound
    2.00
    hounds
    1.98
     hounds
    1.70
     Greyhound
    1.32
    hund
    1.00
     Hund
    0.96
    Hund
    0.85
    Activations Density 0.007%

    No Known Activations