© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5754
    Prev
    Next
    INDEX
    Explanations

    references to experimental methods and comparisons within scientific research

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

    Followed by words like "of", "*", "the", "this"

    np_acts-logits-general · gemini-2.0-flash

    versions of

    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
     spéciaux
    -0.45
     spéciale
    -0.40
     especiales
    -0.39
     apropiado
    -0.37
     correto
    -0.37
     productivo
    -0.34
     supplémentaires
    -0.34
     Juifs
    -0.33
     Abonnez
    -0.32
     práctico
    -0.32
    POSITIVE LOGITS
     disambiguazione
    0.65
    ніципалі
    0.63
     تضيفلها
    0.61
    তথ্যসূত্র
    0.60
    __(/*!
    0.60
     Infórmanos
    0.58
    yarnpkg
    0.57
    featureID
    0.57
     TextAppearance
    0.57
    irie
    0.56
    Activations Density 0.837%

    No Known Activations