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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15582
    Prev
    Next
    INDEX
    Explanations

    snippets of code related to data handling and imports in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code imports and frameworks

    np_acts-logits-general · gemini-2.0-flash

    swift programming imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    httphttps
    -0.39
     equi
    -0.38
    ettbewer
    -0.37
     sco
    -0.36
     pron
    -0.36
    ualaikum
    -0.36
     Szy
    -0.36
     digestive
    -0.36
    ubehör
    -0.35
     igång
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    0.53
    CppMethod
    0.50
    endpush
    0.50
    лтемелер
    0.47
     EconPapers
    0.44
     Drag
    0.44
     endblock
    0.44
    StoryboardSegue
    0.44
     pod
    0.43
     kasarigan
    0.43
    Activations Density 0.166%

    No Known Activations