© 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. 1290
    Prev
    Next
    INDEX
    Explanations

    constructs related to data structures and API requests in programming

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

    Code snippets containing angle brackets

    np_acts-logits-general · gemini-2.0-flash

    programming language constructs

    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
     kasarigan
    -0.60
    (**
    -0.58
    ibrator
    -0.57
    — 
    -0.53
    icksburg
    -0.52
    émica
    -0.52
     typelib
    -0.52
    ]")]
    -0.51
     ***!
    -0.51
     *
    -0.50
    POSITIVE LOGITS
    <
    1.61
     <
    1.03
    <?
    1.00
    .<
    0.81
    ?<
    0.80
    <?>
    0.79
    )<
    0.79
    `<
    0.78
    }<
    0.77
     $<
    0.77
    Activations Density 0.163%

    No Known Activations