© 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-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 8819
    Prev
    Next
    INDEX
    Explanations

    references to validity and the conditions under which certain statements or theories hold true

    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
    antwoorde
    -0.43
    Xna
    -0.43
    comuna
    -0.43
    อย่างไร
    -0.42
    Vanjske
    -0.41
     recherchez
    -0.41
     presença
    -0.40
    homonymie
    -0.40
     partis
    -0.40
    istar
    -0.39
    POSITIVE LOGITS
     validity
    1.77
     valid
    1.75
    valid
    1.57
     Validity
    1.50
    validity
    1.40
     válido
    1.37
    Valid
    1.34
    Validity
    1.32
     valido
    1.31
     Valid
    1.30
    Activations Density 0.742%

    No Known Activations