© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 5665
    Prev
    Next
    INDEX
    Explanations

    elements related to presentation and formatting in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.44
    djangoproject
    -0.35
    انتهای
    -0.34
     createSlice
    -0.33
    setContentView
    -0.33
    hasData
    -0.32
    AutoField
    -0.32
     lienzo
    -0.31
    CreateModel
    -0.31
    zyna
    -0.31
    POSITIVE LOGITS
     highlighted
    1.69
     underlined
    1.63
     highlight
    1.58
     Highlight
    1.46
     highlighting
    1.46
     underline
    1.41
     bold
    1.41
     highlights
    1.40
    highlight
    1.38
    highlighted
    1.36
    Activations Density 0.666%

    No Known Activations