© 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. 19-GEMMASCOPE-RES-16K
    11. 14976
    Prev
    Next
    INDEX
    Explanations

    elements related to email structure and MIME types used for attachments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.84
     __
    -0.76
     Italijanski
    -0.71
    ReusableCell
    -0.71
    ::__
    -0.68
    InitVars
    -0.68
    ьаж
    -0.67
    )__
    -0.66
    MigrationBuilder
    -0.64
     _$
    -0.62
    POSITIVE LOGITS
    原始内容存档于
    0.58
    RectangleBorder
    0.53
    .(
    0.51
    agung
    0.46
    unnitel
    0.43
    $.}
    0.43
    SPATH
    0.42
    GEBURTS
    0.41
    numerusform
    0.41
    ṇa
    0.40
    Activations Density 0.235%

    No Known Activations