© 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. 13-GEMMASCOPE-RES-16K
    11. 2220
    Prev
    Next
    INDEX
    Explanations

    mentions of various approaches or strategies

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Mur
    -0.74
    Mur
    -0.73
     Rosenberg
    -0.69
     tys
    -0.68
     Hickey
    -0.67
    hydr
    -0.65
    égalité
    -0.64
     soldati
    -0.64
     Crum
    -0.63
    weta
    -0.63
    POSITIVE LOGITS
     approaches
    1.56
     Approaches
    1.42
     APPROACH
    1.35
     Approach
    1.33
    Approach
    1.31
     approach
    1.30
    Appro
    1.15
     approached
    1.14
    approach
    1.12
     approaching
    1.04
    Activations Density 0.053%

    No Known Activations