© 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. 105637
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and punctuation used in code

    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
    دانشنامهٔ
    -0.59
    ISupport
    -0.47
    はじめに
    -0.44
     étoient
    -0.42
    Diweddarwch
    -0.41
    RUnlock
    -0.39
     ProtoMessage
    -0.39
    Carriera
    -0.38
    GraphicsUnit
    -0.38
     fotografico
    -0.38
    POSITIVE LOGITS
    iParam
    0.53
    prefixer
    0.48
     kab
    0.44
    rrggbb
    0.43
     đóng
    0.42
     Taktlose
    0.41
     favourably
    0.40
     Kab
    0.40
    holdings
    0.39
     iNdEx
    0.39
    Activations Density 0.007%

    No Known Activations