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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5067
    Prev
    Next
    INDEX
    Explanations

    phrases expressing skepticism or criticism of societal views and historical narratives

    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
    ởi
    -0.54
     AssemblyCompany
    -0.48
     lohnt
    -0.46
     alimentaires
    -0.45
    chec
    -0.45
    ända
    -0.41
     melainkan
    -0.41
     hôtes
    -0.40
    nicki
    -0.40
     lourdes
    -0.40
    POSITIVE LOGITS
     disambiguazione
    0.84
    StructEnd
    0.80
    rungsseite
    0.80
     Roskov
    0.78
     iprot
    0.78
     whining
    0.75
    Personendaten
    0.75
     arrog
    0.75
     blaming
    0.73
     whine
    0.73
    Activations Density 0.503%

    No Known Activations