© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5503
    Prev
    Next
    INDEX
    Explanations

    phrases indicating performance and statistics in sports contexts

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

    "In" followed by statistics or numbers

    np_acts-logits-general · gemini-2.0-flash

    in [time or place]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    Rohy
    -0.50
    ỗng
    -0.39
    npmjs
    -0.37
     disambiguazione
    -0.37
    раздо
    -0.36
     discriminación
    -0.36
    holdet
    -0.36
    Rational
    -0.35
    Rationale
    -0.35
    çoivent
    -0.35
    POSITIVE LOGITS
    XmlAccessType
    0.61
     kasarigan
    0.57
    findpost
    0.43
     оригіналу
    0.43
    BASEPATH
    0.42
    mybatisplus
    0.42
    DebuggerNonUser
    0.41
    newswire
    0.41
    TokenNameLPAREN
    0.40
     menj
    0.40
    Activations Density 0.126%

    No Known Activations