© 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. 9553
    Prev
    Next
    INDEX
    Explanations

    expressions of strong feelings or reactions

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

    exclamatory statements expressing surprise or strong emotion, particularly those beginning with "Wow" or "Boy".

    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
    為主
    -0.42
     moderately
    -0.39
    ❹
    -0.39
     matter
    -0.38
     ویکی‌پدی
    -0.38
    Ӕ
    -0.37
     koska
    -0.37
    Спасылкі
    -0.36
     primarily
    -0.35
    AutoModerator
    -0.35
    POSITIVE LOGITS
     truly
    0.72
    还真是
    0.72
    Truly
    0.69
     davvero
    0.68
     gerçekten
    0.68
    truly
    0.65
     Truly
    0.65
    真是
    0.65
     décid
    0.65
    果然
    0.64
    Activations Density 0.262%

    No Known Activations