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. 6-GEMMASCOPE-RES-16K
    6. 236
    Prev
    Next
    INDEX
    Explanations

    expressions of quantity and variety in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.84
     zijne
    -0.82
    InjectAttribute
    -0.80
     popoli
    -0.76
     quæ
    -0.73
     dezelve
    -0.70
     enfans
    -0.68
     prêtres
    -0.68
     skolan
    -0.67
     Romains
    -0.67
    POSITIVE LOGITS
    OGND
    0.70
    ArrowToggle
    0.70
     kaarangay
    0.69
     SwiftUI
    0.66
    EClass
    0.65
    AddHtmlAttribute
    0.64
     huh
    0.63
     snippetHide
    0.62
     Vikipedi
    0.60
    twimg
    0.59
    Activations Density 0.490%

    No Known Activations