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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1178
    Prev
    Next
    INDEX
    Explanations

    references to figures and tables in academic or research documents

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

    figures or citations

    np_acts-logits-general · gemini-2.0-flash

    citations and bracketed references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    tagHelperRunner
    -0.54
     चीज़ों
    -0.45
    IsContent
    -0.45
    Hozzáférés
    -0.45
    abestanden
    -0.43
    Viited
    -0.39
    EncBinary
    -0.39
    AndEndTag
    -0.39
    writeField
    -0.37
     calefacción
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.65
     PeEnEo
    0.54
     EClass
    0.54
     censiti
    0.48
    webElementXpaths
    0.48
     Италијани
    0.46
    فایل‌لار
    0.44
     referrerpolicy
    0.44
    principalTable
    0.44
    Бахар
    0.44
    Activations Density 0.613%

    No Known Activations