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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10752
    Prev
    Next
    INDEX
    Explanations

    phrases related to individual accountability and risk

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

    phrases expressing risk, consequence, or negative outcome with the pattern "to [their/my/one's] [detriment/peril/chagrin/own]".

    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
    出版年
    -0.60
    saraba
    -0.52
    DockStyle
    -0.49
    sizeCache
    -0.46
    TestingModule
    -0.44
    %)$
    -0.43
    стоин
    -0.41
     rallies
    -0.39
    "?>
    -0.38
     فريبيس
    -0.38
    POSITIVE LOGITS
    
    0.50
     encouragement
    0.43
     ویکی‌پدی
    0.43
     insistence
    0.42
     guidance
    0.42
    +#+#
    0.41
    大家的
    0.41
     expense
    0.41
     satisfaction
    0.40
     benefit
    0.40
    Activations Density 0.372%

    No Known Activations