© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4613
    Prev
    Next
    INDEX
    Explanations

    colons and their related syntactic structures, indicating a focus on programming or data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afficheront
    -0.65
     informée
    -0.63
    出版年
    -0.57
     mergeFrom
    -0.55
    ViewFeatures
    -0.54
     مشين
    -0.54
    principalColumn
    -0.52
    DockStyle
    -0.48
    oredCriteria
    -0.47
     Савезне
    -0.46
    POSITIVE LOGITS
     ::
    2.16
    ::
    2.06
    (::
    1.43
    :::
    1.38
    >::
    1.31
    ::$
    1.26
    ::::
    1.21
    ::_
    1.20
     :::
    1.16
    ::~
    1.01
    Activations Density 0.206%

    No Known Activations