© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 14135
    Prev
    Next
    INDEX
    Explanations

    themes related to emotional complexity and social dilemmas in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.62
     jspb
    -0.61
    DOCTYPE
    -0.60
    IntoConstraints
    -0.57
    GIVEREF
    -0.56
     HFILL
    -0.52
    gbaar
    -0.47
    ślę
    -0.47
    ValueGenerated
    -0.47
    epam
    -0.46
    POSITIVE LOGITS
     cause
    3.13
    cause
    2.83
     Cause
    2.75
    Cause
    2.64
     CAUSE
    2.52
    CAUSE
    2.14
     cuz
    2.05
     causa
    2.00
     coz
    1.94
     cos
    1.91
    Activations Density 0.565%

    No Known Activations