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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11395
    Prev
    Next
    INDEX
    Explanations

    functions and terminology related to parsing

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

    Code parsing or decoding

    np_acts-logits-general · gemini-2.0-flash

    parse, decode, encode

    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
    GenerationType
    -0.76
    AsUp
    -0.71
     Reverso
    -0.66
    +#+#
    -0.65
     numberWith
    -0.65
     ControllerBase
    -0.64
    égek
    -0.63
    Abp
    -0.63
    Facades
    -0.62
    ggiamento
    -0.60
    POSITIVE LOGITS
     Parsing
    0.71
     argparse
    0.70
     解析
    0.68
     ulang
    0.68
     Parse
    0.67
     into
    0.58
     estekak
    0.57
     extracts
    0.57
     Paglinawan
    0.57
     ambiguities
    0.56
    Activations Density 0.235%

    No Known Activations