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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14250
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references, especially related to scores and leads in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >−
    -0.57
     Space
    -0.56
     Leaf
    -0.55
    vs
    -0.54
    èdia
    -0.54
     Th
    -0.52
    HtmlAttribute
    -0.52
    rika
    -0.52
    ว่าง
    -0.52
    ">−
    -0.52
    POSITIVE LOGITS
     chimiques
    0.54
     AppCompatTheme
    0.53
     diarias
    0.52
     endwhile
    0.50
     sauvages
    0.49
     وتسجيلات
    0.48
    UnitId
    0.48
     commerciales
    0.48
     tafel
    0.48
     humaines
    0.48
    Activations Density 0.104%

    No Known Activations