© 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. 21-GEMMASCOPE-RES-16K
    11. 9854
    Prev
    Next
    INDEX
    Explanations

    specific terms and identifiers related to technology or programming, especially those associated with coding and software development

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    openConnection
    -0.49
    BackStack
    -0.45
    fieldLabel
    -0.43
    p
    -0.40
     stanovnika
    -0.40
    profen
    -0.39
     Bioaccumulative
    -0.39
    tisgarh
    -0.38
     ambientale
    -0.37
     dignidad
    -0.36
    POSITIVE LOGITS
    NUMX
    0.81
     Efq
    0.75
     Theſe
    0.75
    ſelves
    0.72
     Dux
    0.72
     ſeveral
    0.70
     Majefty
    0.70
     Diſ
    0.69
     initWithFrame
    0.69
     itſelf
    0.69
    Activations Density 0.260%

    No Known Activations