© 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. 2-GEMMASCOPE-RES-16K
    6. 13111
    Prev
    Next
    INDEX
    Explanations

    terms related to legal exclusions and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.70
    AnchorStyles
    -0.60
    ReusableCell
    -0.57
     للاسماء
    -0.57
    onViewCreated
    -0.56
     للمعارف
    -0.53
     CommonModule
    -0.53
     Photocase
    -0.52
     kasarigan
    -0.51
    HtmlAttribute
    -0.50
    POSITIVE LOGITS
     exclusive
    0.69
     exclu
    0.68
     exclusion
    0.66
    ost
    0.63
     excluir
    0.60
     Exclu
    0.59
     Exclusive
    0.58
     kiz
    0.58
     EXCLUS
    0.58
     exclusives
    0.57
    Activations Density 0.764%

    No Known Activations