© 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. 20-GEMMASCOPE-RES-16K
    11. 5475
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recognize" and its variations, indicating a focus on acknowledgment or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to acknowledgment or identification, particularly in legal or professional contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faudra
    -0.40
    Th
    -0.38
     Polda
    -0.36
        
    -0.36
    ี่ย
    -0.36
    liculas
    -0.35
     eb
    -0.34
    div
    -0.34
     fluff
    -0.33
    getOutputStream
    -0.33
    POSITIVE LOGITS
     recognition
    1.38
     recognize
    1.24
    recognition
    1.23
     Recognition
    1.23
     recognized
    1.20
    recognize
    1.20
     RECOGN
    1.19
     recognise
    1.18
     recognizes
    1.17
     Recognize
    1.16
    Activations Density 0.049%

    No Known Activations