© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15813
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "non" or related prefixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.50
     Erwä
    -0.49
     Beschluss
    -0.48
    tagHelper
    -0.47
     betrekking
    -0.47
    ViewStyle
    -0.47
     izquier
    -0.46
     getTitle
    -0.46
     échanti
    -0.45
     Mayfield
    -0.43
    POSITIVE LOGITS
     Non
    1.31
     non
    1.29
    non
    1.17
    Non
    1.16
     NON
    1.06
    NON
    0.98
     Nons
    0.88
     Nong
    0.82
    nons
    0.82
     nons
    0.80
    Activations Density 0.136%

    No Known Activations