© 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. 5724
    Prev
    Next
    INDEX
    Explanations

    markers or symbols indicating the start or end of content, particularly those used in formatting

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

    Text following certain words (I, Morocco, Generation, Size, Sign, Him)

    np_acts-logits-general · gemini-2.0-flash

    HTML script tags with `ul`

    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
    RegressionTest
    -0.64
    SuppressMessage
    -0.50
    ]]);
    -0.48
    ADVERTISEMENT
    -0.48
    )$;
    -0.48
    LookAnd
    -0.47
    MENAFN
    -0.46
    ogramm
    -0.45
    EDEFAULT
    -0.44
     estre
    -0.44
    POSITIVE LOGITS
     pleaſure
    0.94
     purpoſe
    0.87
     doubtnut
    0.79
     iſt
    0.78
     Jefus
    0.77
    \<^
    0.76
     ſeveral
    0.75
     uſ
    0.75
     itſelf
    0.74
     Chriftian
    0.74
    Activations Density 0.025%

    No Known Activations