© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103281
    Prev
    Next
    INDEX
    Explanations

    references to the word "golden" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikiseite
    -0.58
     Schmerz
    -0.49
     Schuhe
    -0.49
     gitara
    -0.48
    faßt
    -0.48
     Pferd
    -0.48
     Bekasi
    -0.46
    arbeid
    -0.46
     Inscrivez
    -0.46
    føring
    -0.46
    POSITIVE LOGITS
     Golden
    0.97
    <bos>
    0.96
    golden
    0.92
     GOLDEN
    0.90
    Golden
    0.88
     golden
    0.85
    olden
    0.72
    ductory
    0.66
     Vanden
    0.65
     Pomer
    0.65
    Activations Density 0.010%

    No Known Activations