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. 22-GEMMASCOPE-RES-16K
    6. 14007
    Prev
    Next
    INDEX
    Explanations

    mentions of monetary amounts and financial obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esercito
    -0.59
     InputDecoration
    -0.58
    TintMode
    -0.56
     kasarigan
    -0.55
    المناصب
    -0.55
     للمعارف
    -0.55
     defStyleAttr
    -0.54
    Przypisy
    -0.52
    AnchorTagHelper
    -0.52
     FetchType
    -0.52
    POSITIVE LOGITS
     hundreds
    0.59
     Dons
    0.57
    hundreds
    0.55
     thousands
    0.55
     tens
    0.54
     Hundreds
    0.53
     approximately
    0.52
    eabouts
    0.52
    Hundreds
    0.51
     circums
    0.50
    Activations Density 1.209%

    No Known Activations