© 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. 83308
    Prev
    Next
    INDEX
    Explanations

    terms related to time, processes, and duration in various contexts

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

    quantities over time

    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
    ちょうど
    -0.38
    msgTypes
    -0.35
    刚好
    -0.34
    正好
    -0.32
    antaranya
    -0.32
    BeanUtils
    -0.32
     đều
    -0.31
    deux
    -0.29
    剛好
    -0.28
    bungen
    -0.28
    POSITIVE LOGITS
     sometimes
    1.05
     hundreds
    0.98
    hundreds
    0.98
     Hundreds
    0.94
    sometimes
    0.93
     parfois
    0.91
     tens
    0.91
     dizaines
    0.90
     akár
    0.90
     dozens
    0.89
    Activations Density 0.120%

    No Known Activations