© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9471
    Prev
    Next
    INDEX
    Explanations

    references to font styles and weights, particularly bold and variations of fonts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
     UTA
    -0.40
    gelopen
    -0.39
    RefreshLayout
    -0.39
    ordano
    -0.37
     eingel
    -0.36
    SqlClient
    -0.36
     picioare
    -0.36
    mappedBy
    -0.36
     onver
    -0.35
    writerow
    -0.35
    POSITIVE LOGITS
    Bold
    0.77
    fontWeight
    0.72
    bold
    0.72
    BOLD
    0.68
     Bold
    0.65
    setBold
    0.65
     bold
    0.62
     BOLD
    0.61
    styleType
    0.55
     fontWeight
    0.55
    Activations Density 0.340%

    No Known Activations