© 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. 14-GEMMASCOPE-RES-16K
    11. 9221
    Prev
    Next
    INDEX
    Explanations

    instances of the word "speak" and its variations, indicating a focus on communication and expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     Carlton
    -0.60
     Param
    -0.56
     Kits
    -0.56
     RUT
    -0.54
    anganese
    -0.52
     Lafayette
    -0.52
     Jor
    -0.51
    nitrogen
    -0.51
     Haywood
    -0.50
     Juno
    -0.50
    POSITIVE LOGITS
     speak
    1.20
     speaks
    1.11
     Speak
    1.05
     spoken
    1.05
     spoke
    1.04
     speaking
    1.03
    Speak
    1.03
     Speaks
    0.98
    speak
    0.95
     Speaking
    0.90
    Activations Density 0.065%

    No Known Activations