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. 0-GEMMASCOPE-RES-16K
    6. 434
    Prev
    Next
    INDEX
    Explanations

    the phrase "twice" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     szól
    -0.60
    ConfigureAwait
    -0.53
    onesia
    -0.52
    endphp
    -0.51
     ویکی‌پدیای
    -0.51
    ibilité
    -0.51
    usermodel
    -0.50
    طيع
    -0.50
    Agencia
    -0.49
    ungsbedingungen
    -0.49
    POSITIVE LOGITS
     propOrder
    0.77
     <>",
    0.75
     StatelessWidget
    0.73
    homonymie
    0.71
     kasarigan
    0.70
    StoryboardSegue
    0.69
    úgó
    0.67
     TestBed
    0.66
    writeFieldEnd
    0.66
    aarrggbb
    0.66
    Activations Density 0.149%

    No Known Activations