Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3016
    Prev
    Next
    INDEX
    Explanations

    the representation of numerical expressions or calculations

    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
     autorytatywna
    -0.87
    '][]
    -0.86
    Sucesor
    -0.79
    Tracce
    -0.74
    invokeLater
    -0.74
    "):
    
    -0.73
    Tikang
    -0.72
     légales
    -0.72
    [::-
    -0.70
    hoeddwyd
    -0.70
    POSITIVE LOGITS
    1
    1.46
    0
    1.17
    2
    1.06
    st
    1.00
    5
    0.96
    3
    0.92
    6
    0.88
    9
    0.86
    4
    0.84
    8
    0.83
    Activations Density 1.866%

    No Known Activations