© 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. 12-GEMMASCOPE-RES-16K
    6. 5517
    Prev
    Next
    INDEX
    Explanations

    references to company representatives and their testimonies in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urture
    -0.40
    kregen
    -0.36
     BSP
    -0.36
    Спасылкі
    -0.35
    TestingModule
    -0.35
     Cassini
    -0.35
    Уважа
    -0.35
     próximos
    -0.34
    sse
    -0.34
    erapeutics
    -0.34
    POSITIVE LOGITS
    Vidite
    0.50
    staff
    0.47
     staff
    0.46
     executives
    0.46
     ujednoznacz
    0.44
    Билгалдахарш
    0.43
     ſche
    0.42
     dirigeants
    0.42
    Executives
    0.41
    负责人
    0.41
    Activations Density 0.883%

    No Known Activations