© 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. 40-GEMMASCOPE-RES-16K
    11. 7586
    Prev
    Next
    INDEX
    Explanations

    character development and its humanization in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    スタ
    -0.49
    stat
    -0.48
    Sta
    -0.47
     Stati
    -0.45
    station
    -0.43
     sta
    -0.43
    Station
    -0.42
    st
    -0.42
     statis
    -0.41
     Stafford
    -0.41
    POSITIVE LOGITS
     Ste
    2.91
     STE
    2.83
     ste
    2.78
    Ste
    2.77
    STE
    2.48
    ste
    2.34
     Сте
    2.20
     Steve
    2.16
     Stephen
    2.14
     STEV
    2.05
    Activations Density 0.720%

    No Known Activations