© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4359
    Prev
    Next
    INDEX
    Explanations

    technical annotations and metadata in code

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.94
    awtextra
    -0.68
     SUDOC
    -0.60
     betweenstory
    -0.57
     unknownFields
    -0.56
    ⓘ
    -0.55
    usermodel
    -0.52
    ImageContext
    -0.52
    Beau
    -0.51
    v
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.94
    NUMX
    0.84
    __":
    0.71
    --}}
    0.65
     }}$}
    0.64
    daß
    0.64
    Història
    0.63
     laajenta
    0.62
    </tfoot>
    0.61
    ^(@)
    0.60
    Activations Density 0.009%

    No Known Activations