© 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. 18-GEMMASCOPE-RES-16K
    11. 3949
    Prev
    Next
    INDEX
    Explanations

    code annotations and definitions related to database repository classes in a programming context

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

    Java/programming class declarations

    np_acts-logits-general · gemini-2.0-flash

    declaring classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ++)
    -0.83
    ⓘ
    -0.83
     Efq
    -0.82
     &___
    -0.73
    Tembelea
    -0.73
     gynhyrchwyd
    -0.71
       
    -0.69
     ujednoznacz
    -0.68
     = 
    -0.67
    !")
    -0.67
    POSITIVE LOGITS
    fillType
    0.49
    ArgsConstructor
    0.48
     turísticos
    0.38
     sucedido
    0.37
    cím
    0.37
     Champaign
    0.37
     shutters
    0.36
    면
    0.35
    IUrlHelper
    0.35
     domen
    0.35
    Activations Density 0.088%

    No Known Activations