© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7392
    Prev
    Next
    INDEX
    Explanations

    references to governmental councils and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.41
     ausgestattet
    -0.40
     dég
    -0.38
     vorkommen
    -0.38
     Männern
    -0.38
    gehenden
    -0.37
     wuß
    -0.36
     Apertura
    -0.36
    าด
    -0.36
    Quite
    -0.36
    POSITIVE LOGITS
     Council
    0.73
     Alliance
    0.73
     profits
    0.70
     Clan
    0.67
    endregion
    0.67
     council
    0.66
     alliance
    0.65
     clan
    0.60
     Network
    0.60
     coalition
    0.59
    Activations Density 0.265%

    No Known Activations