© 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. 0-GEMMASCOPE-RES-65K
    11. 13419
    Prev
    Next
    INDEX
    Explanations

    words related to methods or indications of progression and potential improvements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    uksessa
    -0.58
    ">//
    -0.55
    dbl
    -0.51
    PRWEB
    -0.51
    cheinend
    -0.50
     chama
    -0.50
    subj
    -0.49
    EVAL
    -0.49
     Normdatei
    -0.49
    γον
    -0.49
    POSITIVE LOGITS
    ReusableCell
    0.77
     jspb
    0.75
     pageContext
    0.72
    pe
    0.69
     ModelExpression
    0.68
    UseVisualStyle
    0.67
    ulite
    0.66
     caj
    0.65
    pees
    0.65
    Externe
    0.65
    Activations Density 0.034%

    No Known Activations