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. 21-GEMMASCOPE-RES-16K
    6. 12432
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extent
    -0.43
    listdir
    -0.42
    Microphone
    -0.41
    Trem
    -0.40
     lắng
    -0.40
    covite
    -0.40
    Consensus
    -0.39
     valt
    -0.39
     boca
    -0.37
     Intens
    -0.37
    POSITIVE LOGITS
     mathematics
    1.36
     mathematical
    1.35
     math
    1.33
     mathematicians
    1.31
     Mathematics
    1.26
     maths
    1.26
     Math
    1.25
     Mathematical
    1.18
    Math
    1.17
     algebra
    1.17
    Activations Density 1.325%

    No Known Activations