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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68604
    Prev
    Next
    INDEX
    Explanations

    key phrases related to change and significant life events

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

    causes user input

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     BoxDecoration
    -0.45
     ligiloj
    -0.45
    verwijspagina
    -0.43
     gärna
    -0.42
     disambiguazione
    -0.41
    farande
    -0.40
    akaian
    -0.38
     âge
    -0.38
     spécial
    -0.38
    >--}}
    -0.38
    POSITIVE LOGITS
    出版年
    0.46
    回
    0.43
     Necessity
    0.42
    pressure
    0.42
    momix
    0.38
     stark
    0.38
     pressure
    0.37
    bootstrapcdn
    0.37
    ⓧ
    0.37
    Obrázky
    0.37
    Activations Density 0.050%

    No Known Activations