© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108568
    Prev
    Next
    INDEX
    Explanations

    questions that inquire about reasons or motivations

    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
    SequentialGroup
    -0.66
     ModelExpression
    -0.66
    parsedMessage
    -0.66
     betweenstory
    -0.65
    IVEREF
    -0.63
    elemField
    -0.61
     Administrativna
    -0.59
    aarrggbb
    -0.59
     StatelessWidget
    -0.58
     dlaczego
    -0.58
    POSITIVE LOGITS
    keit
    0.31
    spartner
    0.30
     journal
    0.28
    alga
    0.28
    Plate
    0.28
     <<<<<<<<<<<<<<
    0.28
     stö
    0.28
    WALL
    0.28
    ness
    0.27
    cti
    0.26
    Activations Density 0.003%

    No Known Activations