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. 15773
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to conditions or criteria for obtaining something

    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
     właśnie
    -0.61
     justement
    -0.59
     justamente
    -0.58
     ilyen
    -0.57
     circonstances
    -0.57
     effectivement
    -0.57
     solchen
    -0.56
    Життєпис
    -0.55
    がこの
    -0.54
    這一
    -0.54
    POSITIVE LOGITS
    writeFieldEnd
    0.88
     Chwiliwch
    0.81
    fillType
    0.74
    Identyfik
    0.74
    WebVitals
    0.73
    =$?
    0.72
    olesale
    0.69
     QName
    0.69
     social
    0.68
     мәкал
    0.68
    Activations Density 0.877%

    No Known Activations