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. 3013
    Prev
    Next
    INDEX
    Explanations

    phrases related to support, research, and the impact of organizations on community health initiatives

    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
    gatsby
    -0.56
    Izvori
    -0.54
    Erreferentziak
    -0.49
     ‘
    -0.47
    Looper
    -0.46
    usto
    -0.46
    appspot
    -0.46
     indeed
    -0.46
    ()['
    -0.46
     UK
    -0.44
    POSITIVE LOGITS
    évaluateur
    0.72
    RegressionTest
    0.67
    DIPSETTING
    0.64
    Gambas
    0.62
    出版年
    0.62
    OrNil
    0.62
     Fiber
    0.62
     Meksiku
    0.61
    rapie
    0.61
    elemField
    0.61
    Activations Density 0.174%

    No Known Activations