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. 10304
    Prev
    Next
    INDEX
    Explanations

    legal terminology and discussions related to judicial processes

    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
     Johnson
    -1.10
    Johnson
    -0.97
     JOHNSON
    -0.96
    johnson
    -0.85
     johnson
    -0.84
    NSON
    -0.77
     Nak
    -0.71
     Andrea
    -0.71
     Erickson
    -0.69
     Savoie
    -0.68
    POSITIVE LOGITS
     Bin
    1.05
     BIN
    1.04
    Hoo
    1.01
     Hoo
    1.00
    Bin
    0.97
     Hoover
    0.89
     bin
    0.86
    BIN
    0.83
     Bobby
    0.82
     Susie
    0.82
    Activations Density 1.594%

    No Known Activations