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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2705
    Prev
    Next
    INDEX
    Explanations

    phrases related to focus and concentration on specific tasks or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cometh
    -0.59
    ltä
    -0.57
     disposent
    -0.52
     tarvit
    -0.52
    cemia
    -0.51
     paik
    -0.50
    kijk
    -0.49
    lack
    -0.48
     Evangelist
    -0.48
     extrapolated
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.83
    +#+#
    0.78
     issues
    0.73
     matters
    0.71
     việc
    0.70
     perfecting
    0.69
     improving
    0.68
     ويكيميديا
    0.67
     ensuring
    0.67
     developing
    0.67
    Activations Density 0.164%

    No Known Activations