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. 21-GEMMASCOPE-RES-16K
    6. 292
    Prev
    Next
    INDEX
    Explanations

    details about property features and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.86
     solteiro
    -0.66
     EoL
    -0.62
     Púb
    -0.62
     básicos
    -0.61
    رشف
    -0.61
     portátiles
    -0.61
     toalha
    -0.60
     amitié
    -0.60
    Népesség
    -0.60
    POSITIVE LOGITS
     custom
    0.95
    custom
    0.73
     Custom
    0.72
     customized
    0.72
    Custom
    0.69
     imported
    0.63
     CUSTOM
    0.63
     customised
    0.62
     bespoke
    0.61
    customized
    0.60
    Activations Density 0.066%

    No Known Activations