© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3861
    Prev
    Next
    INDEX
    Explanations

    keywords related to olfactory processing and sensory experiences

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

    Senses, especially smell and taste

    np_acts-logits-general · gemini-2.0-flash

    senses and sensory perception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    AnchorStyles
    -0.64
    tagHelperRunner
    -0.48
    addy
    -0.46
    ystis
    -0.46
    SourceChecksum
    -0.45
    jai
    -0.45
     demografica
    -0.44
     complic
    -0.42
    migrationBuilder
    -0.42
    oprecip
    -0.42
    POSITIVE LOGITS
     senses
    1.59
     sensory
    1.47
     Senses
    1.46
     taste
    1.33
     sense
    1.29
     Sensory
    1.27
     smell
    1.25
    Sensory
    1.23
     sensorial
    1.23
    sensory
    1.20
    Activations Density 0.364%

    No Known Activations