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. 5031
    Prev
    Next
    INDEX
    Explanations

    numbers and financial figures, particularly in the billions and trillions

    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
     kamp
    -0.47
     camper
    -0.44
     lok
    -0.43
    nette
    -0.42
    rox
    -0.42
    top
    -0.42
    vic
    -0.42
    kamp
    -0.41
     Recu
    -0.41
    PreAuthorize
    -0.41
    POSITIVE LOGITS
     trillion
    1.69
     billion
    1.61
     billions
    1.59
     miliardi
    1.46
    billion
    1.45
     milliards
    1.45
     Milliarden
    1.41
    llion
    1.34
     Billion
    1.29
     milliard
    1.23
    Activations Density 0.117%

    No Known Activations