© 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. 16-GEMMASCOPE-RES-16K
    11. 14394
    Prev
    Next
    INDEX
    Explanations

    links to additional information or services, indicating a focus on context and comprehensive completeness in a text

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

    "And", "much", or similar high frequency words

    np_acts-logits-general · gemini-2.0-flash

    and more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therefore
    -0.52
     geen
    -0.47
    WebElementEntity
    -0.47
    getIs
    -0.46
     pity
    -0.46
     Therefore
    -0.46
    $|
    -0.45
     deshalb
    -0.45
    หน่อย
    -0.44
    자인
    -0.43
    POSITIVE LOGITS
     more
    1.36
     vieles
    1.15
     much
    1.15
     многое
    1.07
     ועוד
    1.04
     mehr
    1.04
    much
    1.03
    more
    1.03
     many
    1.03
     MUCH
    0.98
    Activations Density 0.106%

    No Known Activations