Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 13080
    Prev
    Next
    INDEX
    Explanations

    the beginning or introductory elements of different topics or sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     florales
    -0.41
     verschieden
    -0.39
     sauvages
    -0.38
     sauvage
    -0.38
     iulie
    -0.38
     nejen
    -0.38
    .
    
    -0.38
    ukų
    -0.38
     capuche
    -0.37
     impressed
    -0.37
    POSITIVE LOGITS
     تضيفلها
    0.89
     thì
    0.84
    VIAF
    0.83
    awtextra
    0.78
     tartalomajánló
    0.78
    argout
    0.77
    IntoConstraints
    0.76
     ***!
    0.75
    djangoproject
    0.75
     DbSet
    0.74
    Activations Density 0.644%

    No Known Activations