© 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. 8-GEMMASCOPE-RES-16K
    6. 5026
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating contrasts or differences between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungkinkan
    -0.68
     bezeichneter
    -0.63
    erweise
    -0.61
    jména
    -0.61
    ://"
    -0.60
    ranean
    -0.58
    '
    -0.57
    يئة
    -0.57
    邦
    -0.56
    }'
    -0.55
    POSITIVE LOGITS
     vs
    1.85
     versus
    1.66
     Vs
    1.54
     Versus
    1.50
    versus
    1.42
    vs
    1.35
    Versus
    1.34
     VS
    1.33
     Against
    1.33
    Against
    1.32
    Activations Density 0.138%

    No Known Activations