© 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. 6042
    Prev
    Next
    INDEX
    Explanations

    instances of expressing doubt or uncertainty combined with affirmative statements

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

    Sentences containing contrastive conjunctions

    np_acts-logits-general · gemini-2.0-flash

    concessive 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
    évaluateur
    -0.73
    Leider
    -0.69
     оригіналу
    -0.69
     även
    -0.66
    afficheront
    -0.66
    SuppressMessage
    -0.63
    principalTable
    -0.63
     Правда
    -0.63
    Sadly
    -0.61
    webElementXpaths
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.37
     nevertheless
    1.36
     зато
    1.25
    Nonetheless
    0.98
     immerhin
    0.97
    それでも
    0.96
     zato
    0.95
    Nevertheless
    0.94
     Nevertheless
    0.92
     dennoch
    0.91
    Activations Density 0.265%

    No Known Activations