© 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. 2665
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or health-related research and outcomes

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    focus on or rely on

    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
    hdashline
    -0.72
    RTRS
    -0.63
    tencent
    -0.59
    MemoryStream
    -0.58
    <?=$
    -0.57
     يتيمه
    -0.56
    olesale
    -0.53
    });*/
    -0.52
    Elsewhere
    -0.52
    ṓ
    -0.52
    POSITIVE LOGITS
     towards
    0.67
    towards
    0.59
     principalmente
    0.52
    فایل‌لار
    0.51
     kepada
    0.51
     into
    0.51
     بيها
    0.48
    MessageOf
    0.47
     térm
    0.47
     planification
    0.47
    Activations Density 0.552%

    No Known Activations