© 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. 20-GEMMASCOPE-RES-16K
    6. 11972
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs, particularly focusing on code elements and their functionality in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    complexContent
    -0.58
     kasarigan
    -0.51
    ſelf
    -0.50
    HtmlAttribute
    -0.50
     informée
    -0.49
    
    -0.48
     FetchType
    -0.48
    UrlResolution
    -0.48
    ########.
    -0.48
    UpInside
    -0.46
    POSITIVE LOGITS
     jadx
    0.57
    脚注の使い方
    0.41
    ācijas
    0.40
    ClCompile
    0.40
    high
    0.38
    RESOLVED
    0.37
     fitter
    0.36
     rooting
    0.36
     high
    0.35
     processing
    0.35
    Activations Density 0.556%

    No Known Activations