© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 9682
    Prev
    Next
    INDEX
    Explanations

    significant phrases and structures typical in formal writing or documentation

    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
     ba
    -0.49
     ‘
    -0.49
    得
    -0.45
     d
    -0.44
     For
    -0.43
     ба
    -0.42
     Ba
    -0.41
     realised
    -0.41
     
    -0.41
     (
    -0.41
    POSITIVE LOGITS
     myſelf
    0.89
     AssemblyProduct
    0.88
     ་་
    0.86
     Monfieur
    0.85
    InjectAttribute
    0.84
     Majefty
    0.82
    ſelf
    0.81
    writeField
    0.81
     varandra
    0.79
     itſelf
    0.79
    Activations Density 0.090%

    No Known Activations