© 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. 8392
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "can" indicating capability or possibility

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

    Comes before contractions with "can"

    np_acts-logits-general · gemini-2.0-flash

    can followed by verbs or 't

    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
    bootstrapcdn
    -0.67
     来自
    -0.59
    stdafx
    -0.49
     bidding
    -0.48
    자인
    -0.45
    isbury
    -0.44
     expecting
    -0.42
     Carlyle
    -0.42
     Sta
    -0.42
    })+\
    -0.42
    POSITIVE LOGITS
    ContentAsync
    0.76
     تضيفلها
    0.69
     gynhyrchwyd
    0.69
    parsedMessage
    0.65
    verwijspagina
    0.65
    rungsseite
    0.61
     smell
    0.60
    ₵
    0.60
     Exactos
    0.59
    Cyfeiriadau
    0.57
    Activations Density 0.129%

    No Known Activations