© 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. 1749
    Prev
    Next
    INDEX
    Explanations

    events or milestones related to record achievements

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

    after tokens like "record", "claims", and punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    achieving new records

    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
     autorytatywna
    -0.71
    tdessen
    -0.63
    @[+][
    -0.61
    Autoritní
    -0.54
    Aiheesta
    -0.52
     HttpServlet
    -0.52
     resourceCulture
    -0.51
    IUrlHelper
    -0.51
     outcrops
    -0.51
    ongiorno
    -0.51
    POSITIVE LOGITS
     record
    1.54
     récord
    1.37
     rekord
    1.33
    record
    1.32
     Guinness
    1.31
     records
    1.29
     рекор
    1.23
     Record
    1.20
     RECORD
    1.19
     Rekord
    1.15
    Activations Density 0.201%

    No Known Activations