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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12732
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and numbers or quantity descriptors

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

    "The" followed by a time-related word

    np_acts-logits-general · gemini-2.0-flash

    the/this followed by sequence or time

    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
     Rayleigh
    -0.64
     Adic
    -0.62
    клопе
    -0.60
     uſed
    -0.59
     Cæsar
    -0.59
    ❋
    -0.58
    msgSender
    -0.57
     Reſ
    -0.57
     Paisley
    -0.56
    tocks
    -0.56
    POSITIVE LOGITS
     way
    0.73
     steder
    0.69
    ða
    0.62
    GOTREF
    0.61
    脚注の使い方
    0.60
     мәкал
    0.59
    ajā
    0.59
    -------------</
    0.58
     समीक्षाओं
    0.58
     muualla
    0.56
    Activations Density 0.188%

    No Known Activations