© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104730
    Prev
    Next
    INDEX
    Explanations

    elements related to CSS background properties

    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
    ########.
    -0.82
    AndEndTag
    -0.63
    setVerticalGroup
    -0.62
    amssymb
    -0.60
    ValueStyle
    -0.60
     typelib
    -0.59
     AssemblyCulture
    -0.59
     estekak
    -0.58
    LabelTagHelper
    -0.57
     betweenstory
    -0.54
    POSITIVE LOGITS
    drawable
    0.37
     vectorielle
    0.36
    itattu
    0.35
     transparent
    0.35
     BoxDecoration
    0.34
     background
    0.33
    background
    0.31
     pur
    0.30
    transparent
    0.30
     liquid
    0.30
    Activations Density 0.014%

    No Known Activations