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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2733
    Prev
    Next
    INDEX
    Explanations

    code-related terms and concepts in programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.86
    AddTagHelper
    -0.75
     يتيمه
    -0.71
     Италијани
    -0.66
    TagMode
    -0.66
     ***!
    -0.64
     propOrder
    -0.64
     jadx
    -0.63
    تقاوى
    -0.62
     nakalista
    -0.62
    POSITIVE LOGITS
     vierge
    0.39
     gouverneur
    0.39
     annuel
    0.37
    Title
    0.37
     jugement
    0.37
    Policy
    0.37
    Format
    0.37
    .---
    0.36
    Package
    0.36
    Same
    0.36
    Activations Density 0.195%

    No Known Activations