© 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. 31-GEMMASCOPE-RES-16K
    6. 3568
    Prev
    Next
    INDEX
    Explanations

    references to urban development and community resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to urban development, infrastructure planning, and real estate construction projects.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیای
    -0.38
     NSError
    -0.32
     coupable
    -0.32
     verden
    -0.31
     spéciale
    -0.31
     vectorielles
    -0.29
     préparé
    -0.29
    出版年
    -0.29
     plásticos
    -0.29
     vieilles
    -0.29
    POSITIVE LOGITS
    estrian
    0.68
    SBATCH
    0.67
    
    0.66
     frontage
    0.65
    proposed
    0.65
     незавершена
    0.65
    findpost
    0.64
    Proposed
    0.64
     proposed
    0.63
     Proposed
    0.63
    Activations Density 0.323%

    No Known Activations