© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5891
    Prev
    Next
    INDEX
    Explanations

    function and method calls within programming contexts

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

    Code snippets ending in parentheses

    np_acts-logits-general · gemini-2.0-flash

    function calls with parentheses

    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
    TagMode
    -0.59
     Federal
    -0.49
     !_
    -0.48
    jini
    -0.47
     Cuth
    -0.47
    monių
    -0.46
    ttemberg
    -0.46
     Verder
    -0.45
    گران
    -0.44
     Nee
    -0.43
    POSITIVE LOGITS
    ()
    1.31
    ().
    1.28
    (),
    1.18
    ())
    1.14
    ():
    1.09
    ()
    
    1.08
    ()",
    1.06
    ();
    1.06
    ()}
    1.06
    ());
    1.05
    Activations Density 0.402%

    No Known Activations