© 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. 8-GEMMASCOPE-RES-16K
    11. 12166
    Prev
    Next
    INDEX
    Explanations

    the presence of angled brackets, indicating markup or code elements

    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
     Theſe
    -1.03
     Efq
    -1.00
    featureID
    -0.97
    windowFixed
    -0.96
    transQ
    -0.95
    WriteTagHelper
    -0.94
    AsUp
    -0.93
    setVerticalGroup
    -0.92
    tonode
    -0.90
    ArrowToggle
    -0.89
    POSITIVE LOGITS
    <
    0.96
     <
    0.64
    ><
    0.58
     rowspan
    0.53
    <sub>
    0.50
     $\
    0.50
    //<
    0.49
    |<
    0.46
    \{\\
    0.46
    TagHelper
    0.44
    Activations Density 0.012%

    No Known Activations