© 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 EvalsExportsinterp-engineNEWAPI 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. 12482
    Prev
    Next
    INDEX
    Explanations

    pieces of text relating to help-seeking or assistance requests

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

    Expressing a desire or need

    np_acts-logits-general · gemini-2.0-flash

    expressing wants and intentions

    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
    ---|---|
    -0.36
    pulumi
    -0.33
     Happ
    -0.32
    PTR
    -0.32
     respond
    -0.30
    Enllaces
    -0.30
    Nullable
    -0.30
    vención
    -0.30
    erden
    -0.29
     thro
    -0.29
    POSITIVE LOGITS
     want
    0.87
     wants
    0.87
     wanted
    0.79
     wanting
    0.79
     Want
    0.78
     Wants
    0.77
     desire
    0.75
    want
    0.75
     vouloir
    0.74
     muốn
    0.73
    Activations Density 0.387%

    No Known Activations