© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5848
    Prev
    Next
    INDEX
    Explanations

    key elements related to configuration errors and attributes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ">'+
    -1.23
     "+
    -1.23
     '+
    -1.21
    ='+
    -1.08
    ('+
    -1.05
    ("+
    -1.03
    ="+
    -1.02
    >'+
    -1.01
    /'+
    -1.01
    '+
    -1.01
    POSITIVE LOGITS
     somewhat
    0.84
     bit
    0.75
    somewhat
    0.74
     quite
    0.66
    quite
    0.65
    Quite
    0.63
     Somewhat
    0.62
     Quite
    0.62
     kind
    0.61
     '"
    0.58
    Activations Density 0.206%

    No Known Activations