© 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. 947
    Prev
    Next
    INDEX
    Explanations

    terms related to installation processes and confirmations

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

    Slavic languages and accented characters

    np_acts-logits-general · gemini-2.0-flash

    account confirmed

    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
    /**
    -0.57
    /*
    -0.49
    聞
    -0.47
    ank
    -0.47
    لينا
    -0.46
     surla
    -0.46
    exec
    -0.45
    mon
    -0.44
    break
    -0.43
     screwed
    -0.43
    POSITIVE LOGITS
    +#+#
    0.66
    endpush
    0.64
    loride
    0.63
    راسیون
    0.60
    Телефон
    0.60
     Rptr
    0.59
    enfone
    0.59
    himura
    0.58
    üyada
    0.58
    openzeppelin
    0.56
    Activations Density 0.054%

    No Known Activations