© 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. 108498
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics related to cases or events

    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
     bricolaje
    -0.53
     médicale
    -0.48
     słoń
    -0.47
     sukienka
    -0.45
     humaine
    -0.44
     spéciaux
    -0.44
    ⓘ
    -0.44
     riego
    -0.44
     transparencia
    -0.43
     jengibre
    -0.43
    POSITIVE LOGITS
    enterOuterAlt
    0.65
    DockStyle
    0.43
    ConstraintMaker
    0.41
    mybatisplus
    0.40
     Dance
    0.38
    MarshalTo
    0.38
     ta
    0.37
    AddAttribute
    0.37
    PYX
    0.36
     ven
    0.36
    Activations Density 0.011%

    No Known Activations