© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 400
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their corresponding states or countries

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

    U.S. state abbreviations

    np_acts-logits-general · gemini-2.0-flash

    US states

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     surla
    -1.19
    RetentionPolicy
    -0.85
    %");
    -0.83
    %?
    -0.83
    !")
    -0.80
    ?')
    -0.79
    Personendaten
    -0.79
     []).
    -0.78
    ++);
    -0.77
    ?")
    -0.76
    POSITIVE LOGITS
    .,
    0.65
     USA
    0.63
     where
    0.55
    .
    0.53
     joaat
    0.52
    where
    0.50
     hvor
    0.49
    ;
    0.47
    area
    0.46
     مرئيه
    0.45
    Activations Density 0.200%

    No Known Activations