© 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. 20-GEMMASCOPE-RES-16K
    11. 788
    Prev
    Next
    INDEX
    Explanations

    elements indicative of programming and code structure

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

    Code, ports, or environments

    np_acts-logits-general · gemini-2.0-flash

    configuration and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zuc
    -0.45
    Super
    -0.44
    sen
    -0.43
    ParallelGroup
    -0.43
     Super
    -0.42
    -------
    -0.42
    떻
    -0.41
     super
    -0.41
    アメ
    -0.41
    новниш
    -0.41
    POSITIVE LOGITS
    MemoryWarning
    0.83
     nahilalakip
    0.73
    ✨:
    0.71
     JpaRepository
    0.68
    MockBean
    0.68
    VersionUID
    0.67
     onCreateView
    0.67
    зулта
    0.67
    assertRaises
    0.67
    
    0.66
    Activations Density 0.578%

    No Known Activations