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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2274
    Prev
    Next
    INDEX
    Explanations

    references to testing functionality in code or software

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

    following "Test" or "test"

    np_acts-logits-general · gemini-2.0-flash

    test cases, plans, and functions

    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
    forKey
    -0.68
    océan
    -0.66
    kloped
    -0.66
    ctility
    -0.66
    ombus
    -0.62
    IBLES
    -0.61
    PointerException
    -0.61
    μερα
    -0.60
    phant
    -0.60
    IQR
    -0.59
    POSITIVE LOGITS
    beds
    0.73
     tests
    0.65
     Tests
    0.63
    bed
    0.63
    Tests
    0.58
    UnitTesting
    0.58
     драй
    0.56
    monial
    0.54
     beds
    0.54
    cases
    0.53
    Activations Density 0.164%

    No Known Activations