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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4495
    Prev
    Next
    INDEX
    Explanations

    positive adjectives that convey a sense of adequacy or satisfaction

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

    Comes before an adjective modifying "pretty"

    np_acts-logits-general · gemini-2.0-flash

    pretty or fairly followed by an adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.40
     location
    -0.37
     return
    -0.35
    ان
    -0.34
    ocation
    -0.32
    AtPosition
    -0.32
     MANAGER
    -0.32
        
    -0.31
     alue
    -0.31
    caixa
    -0.31
    POSITIVE LOGITS
     pretty
    1.88
    pretty
    1.86
     Pretty
    1.76
    Pretty
    1.75
     PRET
    1.18
     ziemlich
    1.13
    retty
    1.08
     fairly
    1.04
     Fairly
    0.98
     довольно
    0.98
    Activations Density 0.088%

    No Known Activations