© 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. 13396
    Prev
    Next
    INDEX
    Explanations

    names or references related to individuals or entities

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

    starting with "Sl", "Sne", "Kle", "Blo", or "Fla"

    np_acts-logits-general · gemini-2.0-flash

    common word beginnings

    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
    JsonInclude
    -0.48
     Osborn
    -0.46
    ion
    -0.46
     Kahn
    -0.44
    not
    -0.43
    hoeddwyd
    -0.43
    next
    -0.43
    CDK
    -0.43
    ner
    -0.43
    mint
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.53
    initWithFrame
    0.52
     CURIAM
    0.48
     térmica
    0.46
    PerformLayout
    0.45
     femininas
    0.45
    ViewImports
    0.44
     
    0.44
    éphane
    0.44
     elétrica
    0.43
    Activations Density 0.491%

    No Known Activations