© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9443
    Prev
    Next
    INDEX
    Explanations

    words related to societal structures and interactions

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

    Follows a math problem, Q:, or bracket

    np_acts-logits-general · gemini-2.0-flash

    costly, guilty, hydration

    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
    ing
    -1.19
    🏻
    -1.16
    ative
    -1.11
    ation
    -1.08
    🏼
    -1.07
    aneous
    -1.05
    ations
    -1.01
    ality
    -1.00
    isation
    -1.00
    ously
    -0.99
    POSITIVE LOGITS
    abancı
    0.41
    anskje
    0.40
    achuca
    0.39
    charpe
    0.39
    tymologie
    0.36
     getItemId
    0.36
    angeran
    0.34
    ientôt
    0.34
    pæ
    0.33
    kasse
    0.33
    Activations Density 1.423%

    No Known Activations