© 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. 28-GEMMASCOPE-RES-16K
    11. 3701
    Prev
    Next
    INDEX
    Explanations

    instances of acknowledgment or admission of truth or wrongdoing

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

    Sentences containing "admit" or a synonym

    np_acts-logits-general · gemini-2.0-flash

    admit that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.37
     scrapy
    -0.33
    处
    -0.31
     mys
    -0.31
     Mys
    -0.31
     Drayton
    -0.31
    strokeStyle
    -0.30
     diken
    -0.30
    Normdaten
    -0.30
     puissiez
    -0.30
    POSITIVE LOGITS
     admit
    1.80
     admitting
    1.78
     Admit
    1.64
     admitted
    1.62
     admits
    1.56
     acknowledge
    1.54
     acknowledging
    1.54
     admission
    1.52
     acknowledgment
    1.49
    承认
    1.47
    Activations Density 0.367%

    No Known Activations