© 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. 6098
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements related to lists, enumerations, or clauses

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

    Punctuation followed by conjunctions/transitions

    np_acts-logits-general · gemini-2.0-flash

    contrastive conjunctions or clauses

    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
     beholder
    -0.56
     Leider
    -0.56
    GeneratedValue
    -0.54
    ⓧ
    -0.51
     Meksiku
    -0.50
    rítica
    -0.49
     AUSSI
    -0.48
    CodedInputStream
    -0.47
     LEYENDO
    -0.47
    medriver
    -0.46
    POSITIVE LOGITS
     nor
    1.48
    nor
    1.25
     Nor
    1.09
     Instead
    1.06
     only
    1.06
    而是
    1.04
    only
    1.03
    Nor
    1.02
    代わりに
    0.96
     melainkan
    0.96
    Activations Density 0.346%

    No Known Activations