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. 122992
    Prev
    Next
    INDEX
    Explanations

    references to legal case citations and decisions

    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
    MIDDLEWARE
    -0.40
     Отечественной
    -0.39
    StandardCharsets
    -0.38
     ویکی‌پدیا
    -0.37
    ptons
    -0.36
    Để
    -0.36
     bestem
    -0.36
    chaikovsky
    -0.35
    lapia
    -0.35
    才能
    -0.35
    POSITIVE LOGITS
     jspb
    0.63
    ViewFeatures
    0.54
    RegressionTest
    0.54
     wireType
    0.52
     '\\;'
    0.48
    hoeddwyd
    0.44
    AnchorStyles
    0.44
    ∎
    0.44
     ivelany
    0.42
    DebuggerStep
    0.41
    Activations Density 0.083%

    No Known Activations