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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 57310
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.89
     kasarigan
    -0.49
     AssemblyTitle
    -0.39
    曖昧さ回避
    -0.39
     Audiodateien
    -0.35
    AllowAnonymous
    -0.35
    makeatother
    -0.33
    لينكات
    -0.33
     TestBed
    -0.33
    emlrt
    -0.33
    POSITIVE LOGITS
    HTTPResponse
    1.46
    LayoutPanel
    0.88
    setAccessible
    0.82
    getExternal
    0.82
    CppMethod
    0.78
    typeDefinition
    0.71
     bezeichneter
    0.70
     localObject
    0.70
    InternalFrame
    0.67
     isComment
    0.67
    Activations Density 0.001%

    No Known Activations