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. 25-GEMMASCOPE-RES-16K
    6. 1931
    Prev
    Next
    INDEX
    Explanations

    elements of legal terminology and references to court cases

    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
    hydrogenase
    -0.58
     Munk
    -0.56
     متعلقه
    -0.55
    ⋙
    -0.55
     Taunton
    -0.53
     poveznice
    -0.50
     Thane
    -0.50
    Personensuche
    -0.49
     Nairobi
    -0.49
     Navi
    -0.48
    POSITIVE LOGITS
     Arkansas
    1.48
    Arkansas
    1.30
     Razor
    1.07
     Ark
    1.02
     ARK
    0.96
     Fayetteville
    0.94
    Ark
    0.92
    ARK
    0.89
    Razor
    0.87
     ark
    0.87
    Activations Density 0.180%

    No Known Activations