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. 15763
    Prev
    Next
    INDEX
    Explanations

    elements related to relationships and character interactions in narratives

    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
    ArgsConstructor
    -0.65
     "..\..\..\
    -0.63
     StatelessWidget
    -0.52
    
    -0.49
     pó
    -0.46
    HtmlAttribute
    -0.46
    javadoc
    -0.42
    Compare
    -0.41
     tarvit
    -0.41
     "..\..\
    -0.40
    POSITIVE LOGITS
     soap
    1.15
     Soap
    1.00
     soaps
    0.97
    soap
    0.95
    Soap
    0.85
     soapy
    0.81
    Enders
    0.73
     storyline
    0.72
     Spoilers
    0.72
     daytime
    0.72
    Activations Density 0.062%

    No Known Activations