© 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. 21-GEMMASCOPE-RES-16K
    11. 12849
    Prev
    Next
    INDEX
    Explanations

    programming statements and syntax related to variable declarations and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StartTag
    -0.55
    ("</
    -0.51
     estekak
    -0.49
    .[/
    -0.47
     }}"></
    -0.47
     kasarigan
    -0.46
    andExpect
    -0.46
     الاطلاع
    -0.46
     AssemblyCompany
    -0.46
     مشين
    -0.44
    POSITIVE LOGITS
     cast
    0.66
     operador
    0.64
     function
    0.63
     var
    0.62
     polymorphism
    0.61
     operator
    0.61
     casts
    0.61
     casting
    0.58
     declarar
    0.57
    Skład
    0.57
    Activations Density 1.147%

    No Known Activations