© 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. 18-GEMMASCOPE-RES-16K
    11. 4528
    Prev
    Next
    INDEX
    Explanations

    statements related to intentions and objectives

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

    Statements of purpose or intent

    np_acts-logits-general · gemini-2.0-flash

    identifying purpose and goals

    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
    adaptiveStyles
    -0.77
     typelib
    -0.75
     EconPapers
    -0.75
    ]--;
    -0.75
     ſeveral
    -0.74
     "}";
    -0.72
    )";
    -0.72
     myſelf
    -0.71
    addCriterion
    -0.71
     disambiguazione
    -0.70
    POSITIVE LOGITS
     is
    0.79
    คือ
    0.57
     besteht
    0.56
     заключается
    0.48
     là
    0.47
     darse
    0.45
     состоя
    0.43
     darin
    0.42
     IS
    0.42
    invokeLater
    0.42
    Activations Density 0.289%

    No Known Activations