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. 1607
    Prev
    Next
    INDEX
    Explanations

    references to the United Nations and its activities

    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
    principalTable
    -0.62
     nahilalakip
    -0.58
    principalColumn
    -0.53
    DockStyle
    -0.50
     ब्रेकडाउन
    -0.50
    RefNanny
    -0.48
    Derbyniad
    -0.45
    AntiForgeryToken
    -0.44
    endpush
    -0.43
     catch
    -0.43
    POSITIVE LOGITS
     SRS
    0.47
     Secretary
    0.45
     Resident
    0.44
     OH
    0.40
     Infór
    0.40
     resident
    0.40
     Children
    0.40
     ©️
    0.40
     Security
    0.39
     Guter
    0.39
    Activations Density 0.274%

    No Known Activations