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. 109550
    Prev
    Next
    INDEX
    Explanations

    phrases related to capturing attention and engagement

    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
    uxxxx
    -0.44
    Havolalar
    -0.40
    leyebilirsiniz
    -0.35
    printStats
    -0.34
    vacy
    -0.34
    년
    -0.33
    XmlEnum
    -0.33
    ighborhood
    -0.32
    :"-"`
    -0.32
    %"),
    -0.32
    POSITIVE LOGITS
    Capture
    0.77
     capture
    0.75
     captive
    0.75
     captures
    0.75
     captured
    0.73
     Capture
    0.71
    capture
    0.69
     CAPT
    0.68
     capturing
    0.68
    Captured
    0.65
    Activations Density 0.122%

    No Known Activations