© 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. 25-GEMMASCOPE-RES-16K
    11. 814
    Prev
    Next
    INDEX
    Explanations

    tentative planning and scheduling details related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.73
    PerformLayout
    -0.69
     linkovi
    -0.67
     بيها
    -0.66
    Purchases
    -0.62
    styleType
    -0.61
     abortions
    -0.57
    Transfers
    -0.57
    transfers
    -0.54
     виправивши
    -0.53
    POSITIVE LOGITS
     study
    0.59
     çalışma
    0.58
     interview
    0.58
     project
    0.56
     inspection
    0.56
     viewing
    0.55
     attack
    0.55
     deployment
    0.53
     upgrade
    0.52
     publishing
    0.52
    Activations Density 0.775%

    No Known Activations