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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10672
    Prev
    Next
    INDEX
    Explanations

    references to pages in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esModule
    -0.59
    spelling
    -0.56
    sprechend
    -0.56
     ISNI
    -0.55
    ご了承
    -0.54
    lowercase
    -0.53
    новниш
    -0.53
    сылкі
    -0.53
    FunctionFlags
    -0.53
    tshell
    -0.52
    POSITIVE LOGITS
     getPage
    1.03
     PAGE
    0.93
     pages
    0.90
     Pages
    0.89
     page
    0.82
     Page
    0.81
    PAGE
    0.80
    pages
    0.79
     Pag
    0.78
    Pages
    0.76
    Activations Density 0.119%

    No Known Activations