© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7573
    Prev
    Next
    INDEX
    Explanations

    instances of successful affiliations and achievements in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.65
    出版年
    -0.58
     resourceCulture
    -0.54
    bewerken
    -0.51
    UrlResolution
    -0.51
     loser
    -0.51
    setVerticalGroup
    -0.50
    Personendaten
    -0.50
    richTextPanel
    -0.49
     AssemblyTitle
    -0.47
    POSITIVE LOGITS
     snag
    1.05
     sna
    1.05
     secured
    1.02
     nab
    1.00
     bagged
    0.96
     secure
    0.93
     snatch
    0.92
     secures
    0.88
     bag
    0.88
     snatched
    0.87
    Activations Density 0.313%

    No Known Activations