Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3499
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothing and accessories worn by individuals

    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
    Искәрмәләр
    -0.59
    UiThread
    -0.53
    rungsseite
    -0.51
     couch
    -0.50
     Endpoint
    -0.49
    Enders
    -0.49
     boletín
    -0.49
     Contract
    -0.48
    ContentAsync
    -0.48
    loroethene
    -0.48
    POSITIVE LOGITS
     hat
    1.41
     hats
    1.37
     Hat
    1.24
     Hats
    1.20
    Hat
    1.14
    Hats
    1.13
     brim
    1.11
     HAT
    1.10
    hats
    1.08
     caps
    1.08
    Activations Density 0.191%

    No Known Activations