© 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. 10457
    Prev
    Next
    INDEX
    Explanations

    queries and expressions of uncertainty about what actions to take next

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

    "What to do" or suggestions

    np_acts-logits-general · gemini-2.0-flash

    what to do

    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
    Tembelea
    -0.52
    AddTagHelper
    -0.52
    ➟
    -0.48
     CreateTagHelper
    -0.48
    IVEREF
    -0.48
    Viitteet
    -0.47
    Переваги
    -0.46
    DebuggerNonUser
    -0.46
     Administrativna
    -0.45
     ModelExpression
    -0.45
    POSITIVE LOGITS
     should
    0.82
    Should
    0.78
    should
    0.77
    どうしよう
    0.72
     Should
    0.71
    怎么办
    0.59
     SHOULD
    0.58
    ควร
    0.58
    怎麼辦
    0.54
     Umgang
    0.54
    Activations Density 0.280%

    No Known Activations