© 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. 105820
    Prev
    Next
    INDEX
    Explanations

    references to proofs and their components in mathematical texts

    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
    ollectionView
    -0.58
     viewHolder
    -0.54
    plasia
    -0.54
    DBNull
    -0.53
    URLException
    -0.53
     userType
    -0.52
    alyptus
    -0.52
    CWE
    -0.51
     @"/
    -0.51
    pointments
    -0.51
    POSITIVE LOGITS
     jadx
    0.41
    enumi
    0.41
     penyebab
    0.40
     proof
    0.40
    richTextPanel
    0.39
     Komunikasi
    0.36
     Einführung
    0.36
     confirmación
    0.36
    prozess
    0.35
     absorción
    0.35
    Activations Density 0.062%

    No Known Activations