Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2085
    Prev
    Next
    INDEX
    Explanations

    instances of the word "open" and its variations in various contexts

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

    "open" and its variations

    np_acts-logits-general · gemini-2.0-flash

    open or opening

    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
    rungsseite
    -0.53
     AspNetCore
    -0.53
     Brandt
    -0.53
    copyWith
    -0.47
    apunov
    -0.46
    kirakan
    -0.44
    нью
    -0.44
    polazione
    -0.43
    неш
    -0.43
    mbggenerated
    -0.42
    POSITIVE LOGITS
     doors
    0.88
     Pandora
    0.83
     Opens
    0.82
     lebar
    0.81
     opened
    0.81
    opened
    0.80
     pandora
    0.77
    Opened
    0.76
    Pandora
    0.75
     openings
    0.74
    Activations Density 0.111%

    No Known Activations