© 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. 36-GEMMASCOPE-RES-16K
    6. 15668
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and allegations of misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.45
    Jeografia
    -0.44
     hiszen
    -0.40
    AddTagHelper
    -0.38
    ValueGeneration
    -0.36
    kháu
    -0.35
    帖最后由
    -0.35
    TagMode
    -0.35
    Applicable
    -0.35
    ≦)
    -0.34
    POSITIVE LOGITS
     supposedly
    2.95
     allegedly
    2.81
    supposed
    2.75
     supposed
    2.70
     purported
    2.67
     supuestamente
    2.61
     alleged
    2.56
     reportedly
    2.31
    alleg
    2.06
     suppos
    2.02
    Activations Density 1.241%

    No Known Activations