© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 62872
    Prev
    Next
    INDEX
    Explanations

    references to help and assistance with carrying items

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

    carrying luggage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.45
    WARNINGS
    -0.32
    зулта
    -0.31
    loč
    -0.30
     poésie
    -0.30
     Verf
    -0.30
     oyna
    -0.29
    Fatal
    -0.29
    łego
    -0.28
     freio
    -0.28
    POSITIVE LOGITS
     carrying
    1.66
     Carrying
    1.62
    Carrying
    1.55
     carry
    1.53
    carrying
    1.49
     CARRY
    1.48
    carry
    1.43
     Carry
    1.43
    Carry
    1.43
     carries
    1.32
    Activations Density 0.101%

    No Known Activations