© 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. 12014
    Prev
    Next
    INDEX
    Explanations

    function and variable declarations and their associated operations in programming code

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

    Code related to searching and filtering

    np_acts-logits-general · gemini-2.0-flash

    finding and filtering data

    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
    ContentAsync
    -0.75
    expandindo
    -0.61
    OGND
    -0.61
     SEDS
    -0.58
    extAlignment
    -0.58
    Autoritní
    -0.58
    adaptiveStyles
    -0.56
     nunc
    -0.54
    Diweddarwch
    -0.54
    GEBURTSDATUM
    -0.54
    POSITIVE LOGITS
     find
    1.14
     found
    1.07
     finds
    1.05
    find
    1.04
     search
    1.04
     Find
    1.01
     finding
    0.97
    Find
    0.97
    found
    0.90
     Finds
    0.89
    Activations Density 0.182%

    No Known Activations