© 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. 6647
    Prev
    Next
    INDEX
    Explanations

    references to judgment and perceptions about others

    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
     that
    -2.22
     bahwa
    -1.58
    that
    -1.35
     że
    -1.33
     rằng
    -1.32
     bahawa
    -1.30
     ότι
    -1.27
     kwamba
    -1.22
     dass
    -1.20
     että
    -1.20
    POSITIVE LOGITS
    quels
    0.65
    iencies
    0.54
    wpi
    0.52
    ReusableCell
    0.51
     Bourgoin
    0.50
    afone
    0.49
    enumi
    0.49
    uage
    0.48
    awaiter
    0.48
    idane
    0.46
    Activations Density 0.457%

    No Known Activations