© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 15993
    Prev
    Next
    INDEX
    Explanations

    terms related to expression and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cinogen
    -0.53
    MIDDLEWARE
    -0.52
    CloseOperation
    -0.49
    StreamReader
    -0.49
    awtextra
    -0.48
    WindowConstants
    -0.48
    زيز
    -0.48
     ThemeData
    -0.47
     ddelweddau
    -0.47
    ornment
    -0.46
    POSITIVE LOGITS
     EXPRESS
    1.21
    EXPRESS
    1.15
     expressions
    1.11
    Express
    1.04
     express
    1.02
     Expressions
    1.00
     expr
    0.99
     Express
    0.99
    Expressions
    0.96
     expression
    0.95
    Activations Density 0.124%

    No Known Activations