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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 9096
    Prev
    Next
    INDEX
    Explanations

    references to names and identity related to remembered events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.67
    Autoritní
    -0.63
    BagLayout
    -0.63
    Šaltiniai
    -0.60
    Välislingid
    -0.60
    istoitu
    -0.58
    theless
    -0.57
     δὲ
    -0.57
    eningen
    -0.56
    refour
    -0.54
    POSITIVE LOGITS
     lips
    0.89
     tongue
    0.85
     mouth
    0.84
     mouths
    0.76
     tongues
    0.75
     Tongue
    0.74
    Tongue
    0.70
     labios
    0.69
     pronounce
    0.67
     mention
    0.65
    Activations Density 0.322%

    No Known Activations