Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7301
    Prev
    Next
    INDEX
    Explanations

    names and references related to specific individuals, particularly those with the prefix "Ton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /***/
    -1.01
    DockStyle
    -0.99
    delaire
    -0.93
    INCREF
    -0.91
    ATIVA
    -0.91
     ویکی‌آمباردا
    -0.87
     MainAxisSize
    -0.87
    BagLayout
    -0.87
    ibatis
    -0.86
    IUrlHelper
    -0.82
    POSITIVE LOGITS
     Zon
    1.34
    on
    1.30
     Caron
    1.28
    pon
    1.23
    Zon
    1.19
     Ton
    1.17
     Ston
    1.15
    zon
    1.15
    fon
    1.14
    ion
    1.14
    Activations Density 0.512%

    No Known Activations