© 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. 30-GEMMASCOPE-RES-16K
    11. 13349
    Prev
    Next
    INDEX
    Explanations

    mentions of charitable actions and food distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    giving or contributions

    np_acts-logits-general · gemini-2.0-flash

    donations in past year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revanche
    -0.40
     gada
    -0.36
    hoeddwyd
    -0.36
     engraçadas
    -0.35
    invokeLater
    -0.35
    AutoScaleMode
    -0.35
     schimb
    -0.34
    ografija
    -0.33
    writeField
    -0.33
     namor
    -0.33
    POSITIVE LOGITS
     donated
    1.19
     donations
    1.15
     donation
    1.12
     donating
    1.03
     Donations
    1.02
     donate
    1.02
     distributing
    0.97
    Donations
    0.97
    Donation
    0.95
     distributes
    0.94
    Activations Density 0.193%

    No Known Activations