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. 5-GEMMASCOPE-RES-16K
    6. 3501
    Prev
    Next
    INDEX
    Explanations

    symbols and notation relevant to particle physics and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.85
    Datuak
    -0.78
    GraphicsUnit
    -0.76
    cèse
    -0.75
    webElement
    -0.74
     EconPapers
    -0.74
     calendriers
    -0.74
    FunctionFlags
    -0.72
    تقاوى
    -0.71
     Commencez
    -0.71
    POSITIVE LOGITS
     itſelf
    0.87
     reaſon
    0.83
     reafon
    0.79
     caufe
    0.77
     pamamagitan
    0.73
     purpoſe
    0.73
     ftate
    0.72
     himſelf
    0.71
    seamnă
    0.69
     ſta
    0.68
    Activations Density 0.807%

    No Known Activations