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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 7343
    Prev
    Next
    INDEX
    Explanations

    references to readers, God, and requirements related to life and existence

    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
    +#+#
    -1.07
     мәкал
    -0.84
    InvalidProtocol
    -0.81
    IndentedString
    -0.78
    ArgsConstructor
    -0.73
     Roskov
    -0.72
     Meksiku
    -0.71
    hoeddwyd
    -0.71
    ViewImports
    -0.69
    Geplaatst
    -0.69
    POSITIVE LOGITS
     Theſe
    0.70
     reaſon
    0.64
     Majefty
    0.60
     purpoſe
    0.59
    zelve
    0.55
     qashqai
    0.54
     moindre
    0.54
     ſtre
    0.53
     nombreux
    0.52
     précieux
    0.52
    Activations Density 0.653%

    No Known Activations