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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 12877
    Prev
    Next
    INDEX
    Explanations

    comparative metrics related to gender demographics and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.60
     виправивши
    -0.56
     voudrais
    -0.55
    bewerken
    -0.53
    Vedi
    -0.51
     tartalomajánló
    -0.50
    ształ
    -0.50
    phat
    -0.49
    extAlignment
    -0.49
     Whittier
    -0.48
    POSITIVE LOGITS
     通販
    0.65
     chì
    0.58
    FailureListener
    0.58
    └──
    0.58
    ⓘ
    0.58
     aceptas
    0.57
     Cunningham
    0.54
    CompleteListener
    0.53
     وتسجيلات
    0.52
    cestershire
    0.51
    Activations Density 0.431%

    No Known Activations