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. 12-GEMMASCOPE-RES-16K
    6. 12909
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.74
    :
    -0.69
    ;
    -0.66
    ,
    -0.66
     .
    -0.65
    wnia
    -0.58
    setInput
    -0.57
     fata
    -0.57
    ?
    -0.57
     >
    -0.56
    POSITIVE LOGITS
     فريبيس
    1.25
    __":
    
    1.23
    AddTagHelper
    1.18
    __':
    
    1.18
    AccessorTable
    1.17
    abestanden
    1.09
    expandindo
    1.08
     препратки
    1.03
    UserScript
    1.00
    новниш
    1.00
    Activations Density 0.155%

    No Known Activations