© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3729
    Prev
    Next
    INDEX
    Explanations

    specific product names and technical specifications related to various items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.60
     BoxDecoration
    -0.54
     onlyOwner
    -0.54
    NameInMap
    -0.50
    InSection
    -0.47
    تقاوى
    -0.46
     समीक्षाओं
    -0.46
     Oncol
    -0.46
    KEYCODE
    -0.45
    GEBURTSDATUM
    -0.45
    POSITIVE LOGITS
    esModule
    0.82
    liothèque
    0.61
    phate
    0.59
    eningrad
    0.59
    aticano
    0.59
    beforeSend
    0.58
    IMPORTED
    0.57
    äť
    0.56
    hdashline
    0.56
    manian
    0.54
    Activations Density 0.545%

    No Known Activations