© 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. 7809
    Prev
    Next
    INDEX
    Explanations

    code structures and programming language syntax

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

    Code or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code and programming constructs

    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
    AnchorStyles
    -1.18
    ########.
    -1.17
     متعلقه
    -1.16
    mybatisplus
    -1.10
     BoxFit
    -1.03
    脚注の使い方
    -1.02
    CloseOperation
    -1.00
    extAlignment
    -0.99
     المعيارى
    -0.98
    存于互联网档案馆
    -0.98
    POSITIVE LOGITS
     
    0.83
     "
    0.81
     (
    0.78
     a
    0.71
     “
    0.69
     I
    0.68
     the
    0.68
    ↵↵
    0.64
    ↵
    0.62
     new
    0.62
    Activations Density 1.022%

    No Known Activations