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. 21-GEMMASCOPE-RES-16K
    6. 582
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to Banach spaces and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roli
    -0.47
     carica
    -0.45
    europa
    -0.45
     reconciliation
    -0.44
     sababu
    -0.42
    Aro
    -0.41
    rove
    -0.40
     Massachusetts
    -0.40
     picked
    -0.39
    datatable
    -0.38
    POSITIVE LOGITS
    aarrggbb
    0.87
     mergeFrom
    0.87
     resourceCulture
    0.78
    __':
    
    0.75
     transférez
    0.74
    +#+#
    0.74
    AndEndTag
    0.72
     eventdata
    0.71
     समीक्षाओं
    0.70
     NavController
    0.70
    Activations Density 1.236%

    No Known Activations