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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8128
    Prev
    Next
    INDEX
    Explanations

    phrases that describe unexpected or challenging situations and human struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     counterfe
    -0.37
    sony
    -0.37
     conver
    -0.36
    聊
    -0.34
    বহ
    -0.33
     pediatrician
    -0.33
     Lasso
    -0.33
    feit
    -0.33
     tep
    -0.32
    ckey
    -0.32
    POSITIVE LOGITS
    Tikang
    0.54
    Diweddarwch
    0.52
    iseite
    0.49
     Manusia
    0.49
     typelib
    0.48
    Izvori
    0.47
    évaluateur
    0.47
     sacrificed
    0.47
     réservés
    0.46
     nahilalakip
    0.46
    Activations Density 0.037%

    No Known Activations