© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 13052
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal proceedings or analyses

    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
     autrefois
    -0.84
     ayer
    -0.73
     zuletzt
    -0.71
     last
    -0.66
     kiedyś
    -0.61
     förra
    -0.60
     previamente
    -0.60
     vroeger
    -0.59
    tvguidetime
    -0.59
     yesterday
    -0.59
    POSITIVE LOGITS
     now
    0.62
    +#+#
    0.54
    woor
    0.54
     recollection
    0.53
     defaultstate
    0.51
    now
    0.50
     liệt
    0.50
     owed
    0.48
     craters
    0.48
    grà
    0.48
    Activations Density 1.001%

    No Known Activations