© 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. 24-GEMMASCOPE-RES-16K
    6. 7663
    Prev
    Next
    INDEX
    Explanations

    emotional reactions and expressions of uncertainty

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

    Characters stammering or acting nervous

    np_acts-logits-general · gemini-2.0-flash

    nervousness and hesitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.62
     /\.(
    -0.57
    RegressionTest
    -0.54
    #
    -0.54
    GeneratedCode
    -0.53
     Unido
    -0.53
     predictions
    -0.52
    planung
    -0.52
    Vidite
    -0.52
     препратки
    -0.51
    POSITIVE LOGITS
     stammer
    1.18
     awkward
    1.04
     awkwardly
    1.03
     embarrassed
    0.97
     stutter
    0.93
     stuttering
    0.92
     embarrassment
    0.83
     nervously
    0.83
    Awkward
    0.81
     Embar
    0.80
    Activations Density 0.154%

    No Known Activations