© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 1826
    Prev
    Next
    INDEX
    Explanations

    contextual references to interpersonal interactions and social events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.44
    rungsseite
    -0.36
     شا
    -0.35
     iParam
    -0.35
     <<<<<<<<<<<<<<
    -0.33
     noqa
    -0.32
    SharedCtor
    -0.31
    ViewImports
    -0.30
     Proced
    -0.29
     Entering
    -0.29
    POSITIVE LOGITS
     down
    1.35
     up
    0.94
     giù
    0.93
     upstairs
    0.89
    down
    0.86
    Down
    0.85
     Down
    0.85
     DOWN
    0.82
     downstairs
    0.79
    Upstairs
    0.77
    Activations Density 0.291%

    No Known Activations