© 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. 14583
    Prev
    Next
    INDEX
    Explanations

    code constructs related to function definitions and type declarations

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

    Code or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    typescript code context

    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
     Paglinawan
    -0.53
    новништво
    -0.53
     насељу
    -0.48
     ویکی‌پدی
    -0.47
    mphony
    -0.47
    ScopeManager
    -0.46
    AndEndTag
    -0.46
    вольно
    -0.44
     verá
    -0.44
    gink
    -0.43
    POSITIVE LOGITS
     |
    0.64
     tslint
    0.62
    |
    0.62
     extends
    0.61
    ClientRect
    0.60
     $|
    0.59
    |"
    0.59
     Efq
    0.58
     Monfieur
    0.58
    .|
    0.57
    Activations Density 0.101%

    No Known Activations