© 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 EvalsExportsAPI 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. 109160
    Prev
    Next
    INDEX
    Explanations

    terms related to animal care and rescue

    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
     poffe
    -0.69
     itſelf
    -0.68
     ModelExpression
    -0.65
    IVEREF
    -0.62
     uſed
    -0.62
    ſelf
    -0.60
     raiſ
    -0.59
     houſe
    -0.58
     ſur
    -0.56
     canina
    -0.56
    POSITIVE LOGITS
    hebt
    0.39
     太郎
    0.38
     Belf
    0.37
    Especific
    0.36
    ConstraintLayout
    0.36
     sand
    0.36
    InputBorder
    0.36
    AntiForgeryToken
    0.35
     akad
    0.34
     made
    0.33
    Activations Density 0.009%

    No Known Activations