Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109553
    Prev
    Next
    INDEX
    Explanations

    references to specific series, games, or conventions related to science fiction, particularly "Star Trek."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.60
     createState
    -0.55
    étoit
    -0.55
    ">//
    -0.54
    endphp
    -0.52
     StatelessWidget
    -0.52
    脚注の使い方
    -0.50
     isComment
    -0.50
     leaſt
    -0.48
    reactstrap
    -0.47
    POSITIVE LOGITS
    jMenuItem
    0.36
    ỳ
    0.32
     PUSTAKA
    0.31
     báo
    0.31
     http
    0.31
    setVerticalGroup
    0.30
    memoized
    0.30
    ücksich
    0.30
    CGPoint
    0.30
    XmlAccessorType
    0.29
    Activations Density 0.051%

    No Known Activations