© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2348
    Prev
    Next
    INDEX
    Explanations

    phrases that express different types of "sense" or awareness in various contexts

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

    "sense" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    sense of humor

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    贵
    -0.37
     parati
    -0.36
     export
    -0.36
    Export
    -0.34
    oa̍t
    -0.33
    イ
    -0.32
    export
    -0.32
     routinely
    -0.32
    ๆ
    -0.30
     archipelago
    -0.30
    POSITIVE LOGITS
     sense
    1.80
    sense
    1.72
     Sense
    1.67
    Sense
    1.59
     SENSE
    1.59
     sentido
    1.27
     senso
    1.20
     senses
    1.14
     Senses
    1.05
     sensed
    1.02
    Activations Density 0.149%

    No Known Activations