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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 7639
    Prev
    Next
    INDEX
    Explanations

    expressions related to the characteristics and qualities of objects or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     malheureux
    -0.66
     acrylique
    -0.57
     mourut
    -0.55
     Efq
    -0.54
     leaſt
    -0.53
    panou
    -0.52
    脚注の使い方
    -0.52
    toThrow
    -0.51
     uſe
    -0.51
     كومونز
    -0.50
    POSITIVE LOGITS
    SourceChecksum
    0.75
     uniqueness
    0.63
     بالای
    0.60
     nature
    0.59
    iness
    0.57
    
    0.54
     chóng
    0.54
     géographique
    0.54
     CreateTagHelper
    0.53
    RetentionPolicy
    0.53
    Activations Density 0.276%

    No Known Activations