© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13738
    Prev
    Next
    INDEX
    Explanations

    phrases relating to change in roles or responsibilities within media and entertainment contexts

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

    X Factor or judge-related text

    np_acts-logits-general · gemini-2.0-flash

    X Factor judges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.66
    BeginContext
    -0.66
    üstü
    -0.58
    出版年
    -0.57
     lú
    -0.56
    UpInside
    -0.56
    Chham
    -0.55
    VersionUID
    -0.53
     متعلقه
    -0.53
    +#+#
    -0.52
    POSITIVE LOGITS
     judges
    1.11
     judge
    0.96
    Judges
    0.91
     Judges
    0.89
     jury
    0.83
    jud
    0.82
    judge
    0.81
     judging
    0.77
     contestant
    0.77
     Judge
    0.77
    Activations Density 0.094%

    No Known Activations