© 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-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 7368
    Prev
    Next
    INDEX
    Explanations

    expressions of admiration or attraction

    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
     appeal
    -1.70
     appeals
    -1.53
     appealing
    -1.51
     Appeal
    -1.48
    appeal
    -1.48
     APPEAL
    -1.47
     appealed
    -1.44
    Appeal
    -1.27
     Appeals
    -1.26
    appe
    -1.26
    POSITIVE LOGITS
    OTES
    0.47
    :"-"`
    0.41
     tremp
    0.41
    ɵɵ
    0.40
    uncu
    0.40
     alá
    0.40
     teint
    0.38
     chied
    0.38
     Ciências
    0.37
     voraus
    0.37
    Activations Density 0.319%

    No Known Activations