© 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. 104756
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers in a specific format

    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
    hånd
    -0.42
    mapreduce
    -0.41
    ity
    -0.38
    flo
    -0.37
    ülés
    -0.35
    :✨
    -0.34
    e
    -0.34
    があります
    -0.34
    po
    -0.33
     onPostExecute
    -0.33
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
     geſch
    0.62
     الحره
    0.58
     ſei
    0.58
    BibitemShut
    0.57
    IVEREF
    0.57
    いぐるみ
    0.56
     propOrder
    0.55
     dieſer
    0.55
     dieſem
    0.54
    Activations Density 0.000%

    No Known Activations