© 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. 20-GEMMASCOPE-RES-16K
    6. 3541
    Prev
    Next
    INDEX
    Explanations

    function definitions and control structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming code related to HTTP responses and content handling, especially in web development contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    脚注の使い方
    -0.55
    OGND
    -0.45
    ModelForm
    -0.44
    writeFieldEnd
    -0.42
    出版年
    -0.36
     CreateTagHelper
    -0.36
    vét
    -0.36
    Diweddarwch
    -0.36
     réforme
    -0.35
    erschein
    -0.35
    POSITIVE LOGITS
     ModelAndView
    0.60
    Daf
    0.49
     Daf
    0.48
    ResponseWriter
    0.46
     redirect
    0.46
    ergic
    0.46
    ScopeManager
    0.44
    ftagPool
    0.43
     Commerce
    0.43
    naut
    0.43
    Activations Density 0.111%

    No Known Activations