© 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. 13-GEMMASCOPE-RES-16K
    6. 8782
    Prev
    Next
    INDEX
    Explanations

    references to COVID-19 and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.69
    BindView
    -0.67
    TagMode
    -0.62
     autorytatywna
    -0.61
    SequentialGroup
    -0.59
    makeConstraints
    -0.59
     ModelExpression
    -0.58
     AssemblyTitle
    -0.57
     propOrder
    -0.56
    SourceChecksum
    -0.56
    POSITIVE LOGITS
     corporativa
    0.51
     stationnement
    0.47
     alimentaria
    0.46
     stroom
    0.45
     mellitus
    0.45
     agregado
    0.45
     secours
    0.45
     gravedad
    0.44
     terrorismo
    0.44
    Coronavirus
    0.44
    Activations Density 0.107%

    No Known Activations