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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 12012
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions that involve inequalities and limits

    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
     hason
    -0.53
    胡椒
    -0.53
     resourceCulture
    -0.52
     שוליים
    -0.52
    лосипе
    -0.50
    Clik
    -0.50
    ಉ
    -0.49
    باح
    -0.49
    忑
    -0.48
     nervosa
    -0.47
    POSITIVE LOGITS
    UIControlState
    0.84
    URIComponent
    0.75
     Arquivado
    0.71
     sánh
    0.67
    <%=
    0.63
    istoitu
    0.63
    INCREF
    0.63
     cherchés
    0.63
    intios
    0.62
     '\\;'
    0.62
    Activations Density 0.292%

    No Known Activations