© 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. 10729
    Prev
    Next
    INDEX
    Explanations

    phrases related to hypothetical scenarios or discussions

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

    after "hypothetical"

    np_acts-logits-general · gemini-2.0-flash

    hypothetical children

    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
    Shower
    -0.35
    expr
    -0.34
     pelu
    -0.33
     gethan
    -0.33
    entingan
    -0.33
     shower
    -0.33
    buttonShape
    -0.33
     szóci
    -0.32
     auroit
    -0.31
    amentals
    -0.31
    POSITIVE LOGITS
    contentLoaded
    0.63
     ब्रेकडाउन
    0.60
    Życiorys
    0.57
    MigrationBuilder
    0.51
    MessageOf
    0.50
    PageContext
    0.48
     Winaray
    0.47
    tagext
    0.47
    CloseOperation
    0.47
    UnusedPrivate
    0.45
    Activations Density 1.225%

    No Known Activations