© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3362
    Prev
    Next
    INDEX
    Explanations

    statements of existence or recognition related to subjects and their accomplishments

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

    Follows a form of "is/are" verb

    np_acts-logits-general · gemini-2.0-flash

    is followed by present or past participle

    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
     оригіналу
    -0.76
     autrefois
    -0.65
    Попис
    -0.63
    WriteTagHelper
    -0.63
     kiedyś
    -0.61
     vroeger
    -0.60
     förr
    -0.59
    Viited
    -0.58
    BindingResult
    -0.58
     launched
    -0.58
    POSITIVE LOGITS
     now
    0.73
     currently
    0.71
    Has
    0.68
     presently
    0.63
    currently
    0.62
     owed
    0.60
     owe
    0.58
    now
    0.58
     actuellement
    0.57
    Was
    0.56
    Activations Density 0.525%

    No Known Activations