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. 5832
    Prev
    Next
    INDEX
    Explanations

    terminology related to health and well-being

    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
    theless
    -1.70
    withstanding
    -1.64
    neath
    -1.64
    adays
    -1.40
    selves
    -1.39
    ization
    -1.34
    fraid
    -1.33
    gether
    -1.31
    poptosis
    -1.31
    currency
    -1.29
    POSITIVE LOGITS
    ponym
    0.60
    ouille
    0.52
    kannya
    0.52
    tubers
    0.51
    nemone
    0.51
    chromatic
    0.50
    odyne
    0.50
    memoized
    0.49
    lider
    0.49
    phro
    0.49
    Activations Density 1.811%

    No Known Activations