© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5477
    Prev
    Next
    INDEX
    Explanations

    references to citizenship and identity within various contexts

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

    [word] since

    np_acts-logits-general · gemini-2.0-flash

    activity/state since a past point

    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
    zkod
    -0.56
    findpost
    -0.54
     nanti
    -0.54
    ுகள்
    -0.52
    quale
    -0.50
     prochains
    -0.50
    ]][
    -0.49
    void
    -0.49
    ])[
    -0.47
    })`
    -0.47
    POSITIVE LOGITS
     since
    3.05
    since
    2.68
     SINCE
    2.54
     depuis
    2.32
     Since
    2.27
    Since
    2.27
     sejak
    2.20
     seit
    2.07
     sinds
    1.96
    depuis
    1.92
    Activations Density 0.315%

    No Known Activations