© 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. 7244
    Prev
    Next
    INDEX
    Explanations

    relationships between the body and mind during transitions

    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
    
    -0.40
     pelo
    -0.40
     pous
    -0.38
    ArgsConstructor
    -0.38
    Async
    -0.37
    Parameteri
    -0.37
    ChildScrollView
    -0.36
    ts
    -0.36
     atu
    -0.35
     Detail
    -0.35
    POSITIVE LOGITS
     telling
    1.41
     saying
    1.26
     tells
    1.22
     tell
    1.19
     Telling
    1.17
    Saying
    1.17
     indicating
    1.16
    Telling
    1.16
    tells
    1.15
     Saying
    1.13
    Activations Density 0.674%

    No Known Activations