© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 536
    Prev
    Next
    INDEX
    Explanations

    technical and scientific expressions related to measurements and statistics

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

    meaning "most" or "greatest"

    np_acts-logits-general · gemini-2.0-flash

    most and superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Needless
    -0.48
    出版年
    -0.44
    PRNewswire
    -0.43
     Needless
    -0.43
    分かります
    -0.42
     Stal
    -0.40
     Anz
    -0.40
     sni
    -0.40
     word
    -0.39
     ATT
    -0.38
    POSITIVE LOGITS
     najbardziej
    0.76
    最も
    0.75
     greatest
    0.73
     наиболее
    0.71
     meest
    0.71
     가장
    0.71
     most
    0.70
    が一番
    0.68
     hardest
    0.68
     najwięks
    0.68
    Activations Density 0.500%

    No Known Activations