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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6741
    Prev
    Next
    INDEX
    Explanations

    specific verb forms or phrases across different languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     numerus
    -0.85
     ivelany
    -0.83
    AutoField
    -0.80
    PropertyChanging
    -0.79
     Efq
    -0.78
    tvguidetime
    -0.78
     ब्रेकडाउन
    -0.76
    StoreMessageInfo
    -0.76
    IUrlHelper
    -0.75
    LookAnd
    -0.73
    POSITIVE LOGITS
    asilkan
    0.38
    aguchi
    0.38
    graphql
    0.37
     Hä
    0.36
     ant
    0.36
     scene
    0.36
    sä
    0.35
     dass
    0.35
    scene
    0.35
    <_
    0.35
    Activations Density 0.031%

    No Known Activations