© 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. 2-GEMMASCOPE-RES-16K
    11. 16246
    Prev
    Next
    INDEX
    Explanations

    references to viewers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    σύ
    -0.56
     approach
    -0.52
     tell
    -0.50
     talk
    -0.49
     challenge
    -0.45
    ity
    -0.44
     tip
    -0.44
     Lab
    -0.44
    prisingly
    -0.44
     researchers
    -0.44
    POSITIVE LOGITS
     Viewer
    1.12
    SequentialGroup
    1.02
     viewer
    1.02
     Viewing
    0.97
    Viewer
    0.97
    viewer
    0.96
    viewing
    0.94
    showing
    0.92
     viewing
    0.91
    parsedMessage
    0.91
    Activations Density 0.106%

    No Known Activations