© 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. 39-GEMMASCOPE-RES-16K
    6. 4869
    Prev
    Next
    INDEX
    Explanations

    legal references and case details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.55
    StoryboardSegue
    -0.52
    stateMutability
    -0.50
    randomUUID
    -0.47
    Vene
    -0.45
    Venice
    -0.45
     Dolom
    -0.44
     santiago
    -0.44
    tanleria
    -0.43
     Veneto
    -0.42
    POSITIVE LOGITS
     Kansas
    1.79
    Kansas
    1.66
     KANSAS
    1.45
     Topeka
    1.37
     Wichita
    1.26
     Kans
    1.07
    Wich
    0.96
     KU
    0.93
    ANSAS
    0.91
     Missouri
    0.89
    Activations Density 0.410%

    No Known Activations