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. 15608
    Prev
    Next
    INDEX
    Explanations

    occurrences of curly braces and the keyword "end" relating to structured environments in code or documentation

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

    LaTeX and equation environments

    np_acts-logits-general · gemini-2.0-flash
    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
    CodeAttribute
    -0.49
    UrlResolution
    -0.43
     ContentValues
    -0.42
     resourceCulture
    -0.42
    bcryptjs
    -0.42
    StoryboardSegue
    -0.42
     typelib
    -0.41
     PopupWindow
    -0.41
     <=",
    -0.41
     المعيارى
    -0.41
    POSITIVE LOGITS
    document
    0.49
    XmlAccessorType
    0.47
    Спољашње
    0.45
    abstract
    0.42
     Document
    0.41
     document
    0.40
     Dokumente
    0.40
    DOCUMENT
    0.39
     ExecuteAsync
    0.39
    glBegin
    0.38
    Activations Density 0.009%

    No Known Activations