© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 1726
    Prev
    Next
    INDEX
    Explanations

    sentences that begin with a specific marker or tag, likely indicating the start of a new section or topic

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     künf
    -0.60
    antMatchers
    -0.59
     Tartar
    -0.56
     Remake
    -0.54
     tartalomajánló
    -0.54
     künftig
    -0.53
    Any
    -0.53
     HAP
    -0.52
     DMT
    -0.52
     CPF
    -0.52
    POSITIVE LOGITS
     chi̍t
    0.76
     went
    0.69
     unknownFields
    0.68
    wrote
    0.67
     yesterday
    0.66
     gave
    0.66
     came
    0.65
     Dicapai
    0.65
     wrote
    0.65
    came
    0.65
    Activations Density 0.141%

    No Known Activations