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. 4-GEMMASCOPE-RES-16K
    6. 3388
    Prev
    Next
    INDEX
    Explanations

    references to mathematical equations and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conſ
    -0.81
     ſeveral
    -0.80
     nahilalakip
    -0.78
    neſs
    -0.75
     whoſe
    -0.73
     Perſ
    -0.72
     Diſ
    -0.70
     Jefus
    -0.70
     myſelf
    -0.69
     themſelves
    -0.68
    POSITIVE LOGITS
     equation
    2.64
     equations
    2.54
    equations
    2.28
     Equation
    2.23
    equation
    2.20
    Equation
    2.20
     Equations
    2.19
    Equations
    2.17
    équation
    1.59
    quations
    1.36
    Activations Density 0.177%

    No Known Activations