© 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. 11918
    Prev
    Next
    INDEX
    Explanations

    names of individuals, organizations, or entities in the context of various discussions

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

    Starts with "Gi", "Gy", "Kier", "Li", "Dul", "Hann", "Daw" or "Far"

    np_acts-logits-general · gemini-2.0-flash

    names and places

    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
    sidemargin
    -0.60
    /***/
    -0.56
    awtextra
    -0.55
    ்கள்
    -0.53
    matchCondition
    -0.52
     regolare
    -0.52
     separated
    -0.50
    二是
    -0.49
     different
    -0.49
     or
    -0.47
    POSITIVE LOGITS
    ſſo
    0.55
    ſta
    0.55
    ſo
    0.54
     lenker
    0.53
    wiſe
    0.53
    iſen
    0.53
    ſcher
    0.53
     sulfon
    0.53
     Scin
    0.53
     Wikispecies
    0.53
    Activations Density 0.756%

    No Known Activations