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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92300
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases that indicate continuation and connection in discussions or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    styleUrls
    -0.41
     baloncesto
    -0.38
    toprule
    -0.38
     duração
    -0.38
     inflación
    -0.36
     manuales
    -0.35
     duración
    -0.34
     šk
    -0.34
    PickerController
    -0.34
     först
    -0.34
    POSITIVE LOGITS
     continuation
    0.57
     Continuation
    0.56
    AccessFile
    0.55
     extension
    0.53
    principalColumn
    0.51
    GEBURTSDATUM
    0.50
    CPtr
    0.49
    AddTagHelper
    0.49
    extension
    0.49
    anjutan
    0.49
    Activations Density 0.097%

    No Known Activations