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. 4-GEMMASCOPE-RES-16K
    6. 999
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alternatives or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.77
    quelize
    -0.68
     AssemblyVersion
    -0.66
    تقاوى
    -0.63
     NgModule
    -0.62
     fieldNum
    -0.62
    jspb
    -0.61
    sizeCache
    -0.60
    AccessFile
    -0.58
    QtWidgets
    -0.58
    POSITIVE LOGITS
     Instead
    0.94
    Instead
    0.93
    tdessen
    0.88
     instead
    0.88
    uttosto
    0.76
    instead
    0.75
    而是
    0.72
     Rather
    0.72
     बजाय
    0.71
     istället
    0.69
    Activations Density 0.283%

    No Known Activations