© 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. 0-GEMMASCOPE-RES-16K
    6. 8589
    Prev
    Next
    INDEX
    Explanations

    technical terms and code elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चीज़ों
    -0.65
     Olsson
    -0.62
    protoimpl
    -0.57
    routeProvider
    -0.52
    recovered
    -0.51
    corporated
    -0.51
    lapsingToolbar
    -0.51
    plak
    -0.49
    ACF
    -0.49
     tratt
    -0.48
    POSITIVE LOGITS
    ISupport
    0.66
    getActiveSheet
    0.63
     meth
    0.62
     Razor
    0.61
     endforeach
    0.60
    Repo
    0.59
     Meth
    0.59
     lang
    0.59
     MCC
    0.59
    Попис
    0.58
    Activations Density 2.788%

    No Known Activations