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. 3-GEMMASCOPE-RES-16K
    6. 12367
    Prev
    Next
    INDEX
    Explanations

    words indicating probability or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    D
    -0.57
    C
    -0.57
     Ches
    -0.55
    an
    -0.54
     Z
    -0.53
    tah
    -0.53
    itope
    -0.52
    set
    -0.51
     D
    -0.50
     expansion
    -0.50
    POSITIVE LOGITS
     probably
    3.00
     Probably
    2.80
    probably
    2.70
    Probably
    2.67
     prolly
    2.41
     probablemente
    2.11
     provavelmente
    1.98
     probablement
    1.91
     probabilmente
    1.88
     likely
    1.82
    Activations Density 0.072%

    No Known Activations