© 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. 12191
    Prev
    Next
    INDEX
    Explanations

    references to the importance of research findings and recommendations in various contexts

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

    importance or emphasis

    np_acts-logits-general · gemini-2.0-flash

    highlighting importance

    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
     gespannt
    -0.40
     đương
    -0.36
     uLocal
    -0.36
     الحره
    -0.36
    genöss
    -0.36
    ijakan
    -0.36
     désolés
    -0.35
     putea
    -0.35
    Autoritní
    -0.34
     considérons
    -0.33
    POSITIVE LOGITS
     importance
    2.23
    importance
    1.92
    Importance
    1.91
     Importance
    1.88
     importancia
    1.65
     importância
    1.62
    的重要性
    1.52
    importanza
    1.51
     importanza
    1.38
     اهمیت
    1.33
    Activations Density 0.425%

    No Known Activations