© 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. 20-GEMMASCOPE-RES-16K
    11. 16376
    Prev
    Next
    INDEX
    Explanations

    negative contractions and their usage in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.76
    Slf
    -0.65
    évaluateur
    -0.57
    
    -0.57
     piú
    -0.56
    ますが
    -0.55
    PyExc
    -0.54
    arithmic
    -0.53
    âtre
    -0.53
    ckså
    -0.53
    POSITIVE LOGITS
    <bos>
    0.68
    t
    0.56
    IANGLES
    0.44
     meleg
    0.44
     Stande
    0.44
    Hawai
    0.43
     kube
    0.43
    Borde
    0.42
     sprit
    0.42
     hurt
    0.42
    Activations Density 0.107%

    No Known Activations