© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 12323
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that connect ideas or clauses

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

    Following "and" or "for"

    np_acts-logits-general · gemini-2.0-flash

    and then disincentives or thus

    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
     ModelRenderer
    -0.91
    stdc
    -0.82
    NgModule
    -0.75
    Personensuche
    -0.74
    IntoConstraints
    -0.73
     surla
    -0.71
     NSCoder
    -0.70
     NgModule
    -0.70
    RuleContext
    -0.69
    حوالہ
    -0.69
    POSITIVE LOGITS
    たまた
    0.90
     esterni
    0.68
    </i>
    0.66
     kasarigan
    0.62
    즉
    0.62
    ouille
    0.59
     zwar
    0.54
    hogy
    0.53
    Koordinaten
    0.53
    geordnet
    0.52
    Activations Density 1.444%

    No Known Activations