© 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. 14668
    Prev
    Next
    INDEX
    Explanations

    references to the word "Tal" in various contexts

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

    starting with "Tal" or "Tel"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Tal or Tel

    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
    IUrlHelper
    -0.66
    buttonBar
    -0.56
    Fprintf
    -0.52
    AddWithValue
    -0.51
     Khe
    -0.51
     Crim
    -0.48
    subplots
    -0.48
     StatelessWidget
    -0.48
    Handlung
    -0.47
     StringTokenizer
    -0.47
    POSITIVE LOGITS
    hassee
    0.67
    ented
    0.66
     oprot
    0.56
    mergeFrom
    0.55
     оригіналу
    0.52
     proposito
    0.51
    큼
    0.51
    TextSpan
    0.50
    EntryPoint
    0.47
     père
    0.47
    Activations Density 0.140%

    No Known Activations