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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 220
    Prev
    Next
    INDEX
    Explanations

    specific brands and software names mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to specific individuals and programming-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    cybernet netbook takeoffs centrifugation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]),
    -0.68
     ;
    -0.63
     quæ
    -0.61
     "",
    -0.61
    __":
    -0.60
    />";
    -0.59
     [{
    -0.59
     inoxydable
    -0.58
    ://$
    -0.57
    }");
    -0.57
    POSITIVE LOGITS
     thingy
    0.90
     etc
    0.89
    whatever
    0.88
     stuff
    0.86
     whatever
    0.83
     ANYTHING
    0.82
    etc
    0.81
    bootstrapcdn
    0.80
     anything
    0.79
     anyway
    0.78
    Activations Density 0.090%

    No Known Activations