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. 2256
    Prev
    Next
    INDEX
    Explanations

    numeric values or parameters formatted in specific patterns

    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
    WebElementEntity
    -0.81
    WriteBarrier
    -0.79
    ništvo
    -0.78
     estimés
    -0.75
    ंदीखरीदारी
    -0.75
     linkovi
    -0.72
     كمان
    -0.72
    /**
    -0.69
    errHandler
    -0.67
     reaſon
    -0.66
    POSITIVE LOGITS
    ifolium
    0.49
     campaign
    0.47
     Dec
    0.45
    tyard
    0.45
    /
    0.42
     Campaign
    0.42
     I
    0.42
    ตร์
    0.41
    طقة
    0.40
     “
    0.40
    Activations Density 0.133%

    No Known Activations