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. 1177
    Prev
    Next
    INDEX
    Explanations

    colors and their attributes related to light and shading effects

    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
     sco
    -0.58
    sco
    -0.58
     repri
    -0.56
     parce
    -0.55
    extends
    -0.55
     Lub
    -0.53
     Bex
    -0.53
    γο
    -0.51
    ázaro
    -0.51
    __(/*!
    -0.51
    POSITIVE LOGITS
     myſelf
    0.78
     quæ
    0.73
     réglable
    0.71
    省市镇
    0.70
    niająca
    0.69
     vnto
    0.69
     Monfieur
    0.69
    PageRoute
    0.68
    WebVitals
    0.68
     artificiales
    0.68
    Activations Density 0.090%

    No Known Activations