Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15580
    Prev
    Next
    INDEX
    Explanations

    JavaScript code and jQuery event handling patterns

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

    jQuery code

    np_acts-logits-general · gemini-2.0-flash

    jQuery selectors

    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
    <sup>
    -0.47
     papiers
    -0.46
    edig
    -0.45
    atura
    -0.45
    قص
    -0.44
    ėj
    -0.44
     former
    -0.44
    jetivos
    -0.44
     nullptr
    -0.43
    arsch
    -0.42
    POSITIVE LOGITS
    $(
    0.89
    =$(
    0.85
    $("#
    0.85
    $('#
    0.84
     ($(
    0.84
     $(
    0.84
    ="$(
    0.83
    ($(
    0.82
    Personensuche
    0.80
     الحره
    0.79
    Activations Density 0.149%

    No Known Activations