© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 3494
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with direct actions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omencl
    -0.66
     >=",
    -0.64
     Walkover
    -0.64
    Przypisy
    -0.61
    javadoc
    -0.60
    ModelSerializer
    -0.59
     decorators
    -0.58
     Gazetteer
    -0.58
     initComponents
    -0.58
    uples
    -0.58
    POSITIVE LOGITS
     direct
    1.55
    Direct
    1.54
    DIRECT
    1.44
    direct
    1.44
     DIRECT
    1.40
     Direct
    1.40
     directly
    1.36
     Directly
    1.36
     directa
    1.33
    directly
    1.33
    Activations Density 0.154%

    No Known Activations