© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13337
    Prev
    Next
    INDEX
    Explanations

    concepts related to analysis and reporting of findings in various fields

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    topics for discussion

    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
    .
    -0.68
    帖最后由
    -0.67
     but
    -0.64
     שוליים
    -0.62
    .');
    -0.61
     kaynağından
    -0.61
    NameInMap
    -0.60
    +#+#
    -0.59
    >>();
    -0.58
    matchCondition
    -0.58
    POSITIVE LOGITS
    queryInterface
    0.56
     hierzu
    0.56
     autem
    0.55
     hierbei
    0.55
    therefore
    0.55
     quoque
    0.54
     hierfür
    0.54
    าก็
    0.54
     Anfitrión
    0.53
     nào
    0.53
    Activations Density 1.121%

    No Known Activations