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. 10663
    Prev
    Next
    INDEX
    Explanations

    references to quantitative data and numeric parameters

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

    followed by a negation

    np_acts-logits-general · gemini-2.0-flash

    better change, all unanimously, wrong target

    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
    omg
    -0.59
    enschaften
    -0.54
    Искәрмәләр
    -0.54
    apimachinery
    -0.52
    Omg
    -0.50
    kově
    -0.49
    सन्दर्भ
    -0.49
    typeorm
    -0.49
    OVERALL
    -0.48
    뻐
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.67
    +:+
    0.64
    SourceChecksum
    0.64
    AddTagHelper
    0.63
     оригіналу
    0.63
     oprot
    0.60
    帖最后由
    0.60
     damn
    0.59
    styleType
    0.58
     hyphen
    0.57
    Activations Density 0.554%

    No Known Activations