© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 115479
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or obligation

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

    just have not or just need to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.79
     EconPapers
    -0.75
    ſchaft
    -0.73
     témoig
    -0.70
    ſelves
    -0.69
     faſt
    -0.67
    Архівовано
    -0.66
     tiegħek
    -0.65
    iſchen
    -0.65
    ruptedException
    -0.65
    POSITIVE LOGITS
     Just
    0.73
    Just
    0.71
    just
    0.71
     JUST
    0.69
     just
    0.67
    JUST
    0.55
     juste
    0.49
     justa
    0.43
    st
    0.42
     Simplemente
    0.41
    Activations Density 0.012%

    No Known Activations