© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7358
    Prev
    Next
    INDEX
    Explanations

    concepts and language related to excuses, justifications, and reasons in a legal or personal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.40
     startIndex
    -0.40
     getStart
    -0.38
     onStart
    -0.36
     للاسماء
    -0.35
     popularity
    -0.35
    WriteBarrier
    -0.35
    postIndex
    -0.34
    utenant
    -0.33
    strijden
    -0.33
    POSITIVE LOGITS
     excuses
    1.07
     excuse
    1.05
    excuse
    0.89
     Excuse
    0.81
     excus
    0.81
     reasons
    0.78
     excused
    0.77
     Reasons
    0.75
     reason
    0.71
    Reasons
    0.70
    Activations Density 0.869%

    No Known Activations