© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15131
    Prev
    Next
    INDEX
    Explanations

    specific attributes or characteristics related to biological and mechanical components

    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
    LookAnd
    -1.10
    adpleegd
    -1.06
     للاسماء
    -0.98
     disponibilités
    -0.95
    :✨
    -0.90
     Италијани
    -0.90
    Personensuche
    -0.89
     '\\;'
    -0.89
    transQ
    -0.89
     ویکی‌پدی
    -0.89
    POSITIVE LOGITS
    LOOKUP
    0.44
    Clear
    0.44
     chiar
    0.41
    /
    0.41
    CLEAR
    0.40
    TestingModule
    0.39
     Clear
    0.38
    nek
    0.38
     semula
    0.37
     mourut
    0.37
    Activations Density 1.344%

    No Known Activations