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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2284
    Prev
    Next
    INDEX
    Explanations

    references to social media interactions and company information

    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
    ...)
    -0.46
    ...");
    -0.46
    tyg
    -0.42
    ...')
    -0.42
     Cár
    -0.42
     vulgaires
    -0.42
    lês
    -0.41
    cill
    -0.41
    而已
    -0.41
    χω
    -0.41
    POSITIVE LOGITS
     Twitter
    1.28
     twitter
    1.27
    Twitter
    1.21
    twitter
    1.17
     tweets
    1.16
     (@
    1.15
     @
    1.14
     tweeting
    1.12
     Facebook
    1.06
     instagram
    1.05
    Activations Density 0.075%

    No Known Activations