Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3736
    Prev
    Next
    INDEX
    Explanations

    closing brackets or parentheses in code syntax

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

    Code containing "continue" statements

    np_acts-logits-general · gemini-2.0-flash

    continue keyword in code

    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
    basicConfig
    -0.79
    featureID
    -0.72
     betweenstory
    -0.65
     Савезне
    -0.64
    EndGlobalSection
    -0.63
    addCriterion
    -0.61
     nahilalakip
    -0.60
    intios
    -0.60
    Portail
    -0.59
    Искәрмәләр
    -0.58
    POSITIVE LOGITS
    continue
    3.31
     continue
    3.18
     continued
    3.17
     continues
    2.91
     continuing
    2.84
    continued
    2.74
     Continue
    2.58
     Continued
    2.55
    Continued
    2.46
    continues
    2.45
    Activations Density 0.120%

    No Known Activations