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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 4659
    Prev
    Next
    INDEX
    Explanations

    instances of the word "once" and similar terms indicating conditional or sequential events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scroller
    -0.56
    resar
    -0.52
    íná
    -0.46
    stylers
    -0.45
     věci
    -0.45
    liosis
    -0.45
     Córdoba
    -0.45
    hability
    -0.44
    私には
    -0.44
    Burt
    -0.43
    POSITIVE LOGITS
     Once
    1.03
    Once
    0.99
    ONCE
    0.92
     once
    0.92
    once
    0.86
     Setelah
    0.86
    一旦
    0.83
     Sobald
    0.83
     sobald
    0.80
    enumi
    0.78
    Activations Density 0.176%

    No Known Activations