© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 71
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lorus
    -0.43
     秀
    -0.42
    van
    -0.42
    нгредіє
    -0.39
    انه
    -0.38
     Audiodateien
    -0.38
    ElementException
    -0.38
    økt
    -0.38
    瑕
    -0.38
    ੌ
    -0.37
    POSITIVE LOGITS
     mapping
    1.47
     map
    1.36
     table
    1.31
    mapping
    1.30
     mappings
    1.26
     Mapping
    1.24
    Mapping
    1.18
    Map
    1.17
     maps
    1.16
    map
    1.16
    Activations Density 0.436%

    No Known Activations