© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16136
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax within programming examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.41
    ↵↵
    -0.40
     mimpi
    -0.39
     keluarganya
    -0.39
     zorgen
    -0.38
     asesinado
    -0.37
     chargée
    -0.37
     kekasih
    -0.36
     bekym
    -0.36
    orologio
    -0.36
    POSITIVE LOGITS
    httphttps
    0.70
    
    0.68
    tagHelperRunner
    0.65
    findpost
    0.65
    WriteTagHelper
    0.64
    RenderAtEndOf
    0.60
    IGraphics
    0.60
    脚注の使い方
    0.60
    AddTagHelper
    0.58
    webElement
    0.57
    Activations Density 0.106%

    No Known Activations