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. 25-GEMMASCOPE-RES-16K
    6. 10310
    Prev
    Next
    INDEX
    Explanations

    specific DNA sequences and their mutations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withstanding
    -1.06
    foundland
    -0.95
    которые
    -0.90
    envolvimento
    -0.81
    pography
    -0.72
    vereign
    -0.71
    fraid
    -0.68
    nadequate
    -0.66
    FundMe
    -0.65
    poptosis
    -0.64
    POSITIVE LOGITS
    k
    0.80
    d
    0.74
    f
    0.71
    tualmente
    0.67
    g
    0.62
    p
    0.62
    c
    0.61
    OfWeek
    0.57
    j
    0.56
    словия
    0.55
    Activations Density 0.702%

    No Known Activations