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. 7-GEMMASCOPE-RES-16K
    6. 8716
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific and technical specifications or identifiers

    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
     mapStateToProps
    -0.85
    AccessFile
    -0.84
     >=",
    -0.80
     nahilalakip
    -0.80
    mapStateToProps
    -0.79
     تعدى
    -0.73
    RunAsync
    -0.71
    tvguidetime
    -0.70
     ControllerBase
    -0.69
    tagHelper
    -0.69
    POSITIVE LOGITS
     ECS
    0.97
     Egger
    0.92
     EG
    0.90
     Estrada
    0.87
     Esk
    0.87
     Ema
    0.86
     Elia
    0.85
     Elias
    0.84
     Easton
    0.84
     EA
    0.83
    Activations Density 2.421%

    No Known Activations