© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7864
    Prev
    Next
    INDEX
    Explanations

    terms related to legislative processes and people's ability to express their opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finally
    -0.62
    finally
    -0.57
     besonders
    -0.56
    終於
    -0.56
     finalmente
    -0.54
    とにかく
    -0.54
    Finally
    -0.54
    Really
    -0.53
     möglichst
    -0.52
     Finally
    -0.51
    POSITIVE LOGITS
     plenty
    1.25
     perfectly
    1.19
     вполне
    1.13
     perfectamente
    1.12
    plenty
    1.11
    Plenty
    1.05
    perfectly
    1.03
     Plenty
    1.00
     Perfectly
    1.00
     perfeitamente
    0.97
    Activations Density 1.067%

    No Known Activations