© 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. 24-GEMMASCOPE-RES-16K
    11. 6530
    Prev
    Next
    INDEX
    Explanations

    inquiries into causes and explanations for observed phenomena

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

    "Explain" or "why" questions

    np_acts-logits-general · gemini-2.0-flash

    explains why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.56
     autorytatywna
    -0.52
    참고
    -0.50
    ########.
    -0.48
    \{\\
    -0.48
    XtraBars
    -0.46
    GeneratedMessage
    -0.45
     MaterialApp
    -0.45
    disposing
    -0.44
    الحياه
    -0.43
    POSITIVE LOGITS
     why
    0.87
     warum
    0.71
    为何
    0.69
    why
    0.69
     mengapa
    0.65
    为什么
    0.65
     varför
    0.64
     hvorfor
    0.61
     waarom
    0.61
     pourquoi
    0.61
    Activations Density 0.529%

    No Known Activations