© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15817
    Prev
    Next
    INDEX
    Explanations

    assertions or conclusions related to research findings

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

    Code, commands, or technical language

    np_acts-logits-general · gemini-2.0-flash

    determining connected structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.95
    تقاوى
    -0.84
     AspNetCore
    -0.83
    )";
    -0.78
    󠁮
    -0.76
    ).]
    -0.76
     NDEBUG
    -0.76
    +#+#
    -0.75
    MigrationBuilder
    -0.74
    ]-->
    -0.70
    POSITIVE LOGITS
    </i>
    0.61
     betweenstory
    0.50
    oredCriteria
    0.48
     Numerade
    0.48
    例文帳に追加
    0.47
     ...
    0.46
     autorytatywna
    0.45
    <b>
    0.44
    protoc
    0.44
    FieldNumber
    0.44
    Activations Density 7.491%

    No Known Activations