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. 2-GEMMASCOPE-RES-16K
    6. 6384
    Prev
    Next
    INDEX
    Explanations

    commands or phrases indicating initiation or beginning actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.75
     actualité
    -0.70
    Errorf
    -0.68
    
    -0.68
     contentType
    -0.66
    tiker
    -0.66
     Waray
    -0.65
     Professions
    -0.63
    بوابة
    -0.63
     numberWith
    -0.62
    POSITIVE LOGITS
     start
    2.21
     started
    2.03
     starts
    1.99
     starting
    1.86
     Start
    1.82
     Starts
    1.71
     begin
    1.68
     START
    1.63
     Started
    1.61
    started
    1.60
    Activations Density 0.103%

    No Known Activations