© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4460
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to examination and analysis processes

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

    checking or reviewing

    np_acts-logits-general · gemini-2.0-flash

    examining for existence

    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
     detectable
    -0.52
     unto
    -0.50
    oredCriteria
    -0.48
     réussi
    -0.47
    первых
    -0.46
     كنت
    -0.46
     gesuchten
    -0.45
     oublier
    -0.45
    inaudible
    -0.44
    さえ
    -0.44
    POSITIVE LOGITS
     whether
    0.93
    是否有
    0.88
     carefully
    0.85
     thoroughly
    0.84
     exhaus
    0.82
     intensively
    0.81
    whether
    0.79
    是否
    0.79
    是否存在
    0.78
    有没有
    0.77
    Activations Density 0.600%

    No Known Activations