© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104508
    Prev
    Next
    INDEX
    Explanations

    various visual representations and relationships depicted in diagrams and plots

    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
    ########.
    -0.67
    الحياه
    -0.67
     Chwiliwch
    -0.64
    sizeCache
    -0.61
     ExecuteAsync
    -0.60
     gynhyrchwyd
    -0.60
    السكان
    -0.59
     InputDecoration
    -0.59
    contentLoaded
    -0.57
     ***!
    -0.57
    POSITIVE LOGITS
     entrance
    0.34
    дравству
    0.31
     normalidad
    0.29
     struck
    0.29
     hề
    0.29
     hva
    0.28
     Driscoll
    0.28
    documentclass
    0.28
     expected
    0.28
     suggested
    0.27
    Activations Density 0.073%

    No Known Activations