© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4757
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to scores and performance metrics

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

    numbers; double, triple, digits

    np_acts-logits-general · gemini-2.0-flash

    double, triple, single numbers

    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
     Wikimedijinoj
    -0.79
     âgées
    -0.60
     religieuses
    -0.58
     surla
    -0.57
    Viitteet
    -0.57
    存于互联网档案馆
    -0.55
    webElementXpaths
    -0.53
    PerformLayout
    -0.52
     picioare
    -0.52
     coel
    -0.52
    POSITIVE LOGITS
     double
    1.10
     mid
    0.97
    double
    0.88
     single
    0.87
     teens
    0.84
     triple
    0.82
     upper
    0.81
     low
    0.76
    RectangleBorder
    0.74
     digits
    0.74
    Activations Density 0.153%

    No Known Activations