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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16295
    Prev
    Next
    INDEX
    Explanations

    references to endings and conclusions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.55
     Italijanski
    -0.49
    astéroïdes
    -0.46
    AnimationsModule
    -0.46
    Tikang
    -0.45
    findpost
    -0.44
    jspx
    -0.43
    VersionUID
    -0.43
    WebServlet
    -0.42
     indisponible
    -0.42
    POSITIVE LOGITS
     end
    1.84
     akhir
    1.45
     ending
    1.45
     koniec
    1.40
     پایان
    1.39
     конце
    1.38
     slutet
    1.34
     Ende
    1.33
     cuối
    1.29
     End
    1.25
    Activations Density 0.805%

    No Known Activations