© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 10410
    Prev
    Next
    INDEX
    Explanations

    references to sensory experiences and perceptions

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

    "sense of"

    np_acts-logits-general · gemini-2.0-flash

    sense of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.44
    enquête
    -0.38
     diary
    -0.37
    lüğ
    -0.37
     tiroirs
    -0.36
     tangan
    -0.36
    矶
    -0.35
     Reihen
    -0.35
     Wilton
    -0.35
    Би
    -0.34
    POSITIVE LOGITS
     Sense
    0.97
    sense
    0.92
     SENSE
    0.87
    Sense
    0.87
     sense
    0.82
    concept
    0.80
    Concept
    0.79
     Senses
    0.79
     Concept
    0.77
     Sensor
    0.76
    Activations Density 0.124%

    No Known Activations