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. 20-GEMMASCOPE-RES-16K
    6. 8954
    Prev
    Next
    INDEX
    Explanations

    temporal concepts related to duration and intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.61
    Personendaten
    -0.57
     chi̍t
    -0.56
    roides
    -0.56
    nicity
    -0.53
    hikari
    -0.53
    ividual
    -0.53
     IActionResult
    -0.52
    writeFieldEnd
    -0.51
    ==="
    -0.49
    POSITIVE LOGITS
     until
    1.14
     since
    1.05
     till
    0.95
     Until
    0.95
    until
    0.94
    since
    0.93
    Until
    0.93
     between
    0.86
     untill
    0.82
     before
    0.81
    Activations Density 0.249%

    No Known Activations