© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8340
    Prev
    Next
    INDEX
    Explanations

    references to 'anchor' and 'treasure' within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    Jîn
    -0.43
    setCellStyle
    -0.37
    RTLI
    -0.36
     ReactDOM
    -0.35
     requestId
    -0.35
    ToInt
    -0.35
    CardBody
    -0.33
    ClInclude
    -0.33
     ơi
    -0.33
    Cop
    -0.33
    POSITIVE LOGITS
     treasure
    1.23
    treasure
    1.02
     Treasure
    1.00
    Treasure
    0.92
     TREAS
    0.91
     treasury
    0.88
     treasures
    0.86
     Treasury
    0.85
     anchor
    0.83
     treas
    0.83
    Activations Density 0.411%

    No Known Activations