© 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-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 9618
    Prev
    Next
    INDEX
    Explanations

    instances of the word "express" and its variations, indicating a focus on the theme of communication and personal expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Neutron
    -0.54
     برانيه
    -0.54
     auri
    -0.53
     pouvoit
    -0.50
    août
    -0.50
    IfNot
    -0.49
     Karo
    -0.49
     anemia
    -0.48
     neutron
    -0.48
    dust
    -0.48
    POSITIVE LOGITS
     express
    1.45
     expression
    1.41
     EXPRESS
    1.35
     Express
    1.34
    express
    1.32
    Express
    1.28
     expressions
    1.27
     Expression
    1.24
     expresses
    1.23
     expressed
    1.22
    Activations Density 0.147%

    No Known Activations