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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 11652
    Prev
    Next
    INDEX
    Explanations

    instances of profanity and offensive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.96
    ]='\
    -0.73
    TestBed
    -0.69
    WithIOException
    -0.68
     bershka
    -0.66
    SOUNDBITE
    -0.65
     iNdEx
    -0.64
    __':
    
    -0.63
    inguém
    -0.62
     Moskva
    -0.61
    POSITIVE LOGITS
     swear
    1.07
     swearing
    1.04
     swears
    1.00
     explicit
    0.89
     vulgar
    0.85
     prof
    0.85
     swore
    0.82
     language
    0.81
     NSFW
    0.79
     obscene
    0.79
    Activations Density 0.158%

    No Known Activations