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. 7687
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to software installation issues and successes

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

    Action or process being successful

    np_acts-logits-general · gemini-2.0-flash

    successful and smooth operations

    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
    どうしても
    -0.65
     inability
    -0.60
     невозможно
    -0.55
     нельзя
    -0.54
    就不能
    -0.53
    XmlAccessorType
    -0.53
     оригіналу
    -0.52
    cannot
    -0.52
     impractical
    -0.52
     cannot
    -0.52
    POSITIVE LOGITS
     successfully
    1.33
     satisfactorily
    1.31
     smoothly
    1.27
     flawlessly
    1.23
     satisfactory
    1.21
     problemlos
    1.15
     flawless
    1.14
     Successfully
    1.12
     undamaged
    1.11
     successful
    1.11
    Activations Density 1.007%

    No Known Activations