Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5901
    Prev
    Next
    INDEX
    Explanations

    text related to authors, titles, and publication details in literary contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.40
    IonicModule
    -0.35
     Wiktionnaire
    -0.33
    новниш
    -0.31
    лтемелер
    -0.31
    sizeCache
    -0.30
    IndentedString
    -0.30
    sidemargin
    -0.30
    msgTypes
    -0.30
    InputBorder
    -0.30
    POSITIVE LOGITS
     Könige
    0.40
     Económica
    0.40
     katholischen
    0.39
     kathol
    0.39
     Erzb
    0.37
     Spitze
    0.36
     Gegend
    0.36
     mittelalter
    0.34
     lentejuelas
    0.33
     Feinde
    0.33
    Activations Density 1.805%

    No Known Activations