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. 14185
    Prev
    Next
    INDEX
    Explanations

    phrases indicating geographic directions or positions

    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
    File
    -0.49
    asso
    -0.48
     sal
    -0.47
     dry
    -0.45
     special
    -0.45
    Sal
    -0.45
     fä
    -0.45
    มากกว่า
    -0.45
     any
    -0.44
     Che
    -0.44
    POSITIVE LOGITS
    elemField
    0.97
    Geplaatst
    0.93
    новниш
    0.87
     للاسماء
    0.84
     resourceCulture
    0.79
    AddTagHelper
    0.78
    StoryboardSegue
    0.77
    oa̍t
    0.77
     Baillargeon
    0.77
     mxArray
    0.76
    Activations Density 0.183%

    No Known Activations