© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101897
    Prev
    Next
    INDEX
    Explanations

    the presence of specific programming commands related to writing attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setContentView
    -0.40
     OTHERS
    -0.37
    setLong
    -0.37
     Fong
    -0.35
     Others
    -0.35
    ége
    -0.34
     Agent
    -0.33
    ⓘ
    -0.33
    zlich
    -0.33
     espada
    -0.33
    POSITIVE LOGITS
    WriteAttribute
    5.94
    AddHtmlAttribute
    1.72
     CreateTagHelper
    1.16
    AddTagHelper
    1.05
    ValueStyle
    0.97
     Empieza
    0.94
    ScopeManager
    0.91
    EndContext
    0.90
    awtextra
    0.89
    TagMode
    0.88
    Activations Density 0.000%

    No Known Activations