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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 718
    Prev
    Next
    INDEX
    Explanations

    URLs or links to various web resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.75
     UnityEditor
    -0.73
    ArgsConstructor
    -0.70
     EdgeInsets
    -0.69
     BoxDecoration
    -0.68
     Majefty
    -0.63
     SRT
    -0.63
     laver
    -0.62
     Hoh
    -0.62
     Offen
    -0.62
    POSITIVE LOGITS
     link
    1.47
     Link
    1.47
     LINK
    1.46
     links
    1.43
    links
    1.34
    link
    1.29
     Links
    1.29
    Link
    1.26
    LINK
    1.26
     LINKS
    1.21
    Activations Density 0.066%

    No Known Activations