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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 120347
    Prev
    Next
    INDEX
    Explanations

    occurrences of email addresses and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     nouveautés
    -0.37
     Pública
    -0.35
     montagna
    -0.35
     bahía
    -0.34
     intérieure
    -0.34
    ,
    -0.34
     recev
    -0.34
     prochaines
    -0.33
     fija
    -0.33
     dø
    -0.33
    POSITIVE LOGITS
    rungsseite
    0.90
     AssemblyCompany
    0.85
    出版年
    0.77
    #+#
    0.76
     utafitiHapana
    0.73
    Tikang
    0.73
     kasarigan
    0.72
    +#+
    0.66
    脚注の使い方
    0.66
    basicConfig
    0.65
    Activations Density 0.009%

    No Known Activations