© 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. 31-GEMMASCOPE-RES-16K
    11. 2652
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or present content

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

    introductory phrases that precede quoted text or excerpts (like "Here's").

    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
     للاسماء
    -0.78
     ویکی‌پدی
    -0.65
    StructEnd
    -0.63
    Jeografia
    -0.60
    :✨
    -0.60
    ⟬
    -0.58
    锈钢
    -0.58
    Хьажоргаш
    -0.57
     arşivlendi
    -0.56
     kohdetta
    -0.56
    POSITIVE LOGITS
     what
    0.57
     how
    0.52
     some
    0.52
     proof
    0.51
     hoping
    0.50
     why
    0.49
     where
    0.47
     another
    0.43
     link
    0.40
    where
    0.39
    Activations Density 0.115%

    No Known Activations