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. 0-GEMMASCOPE-RES-16K
    6. 7941
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or technical code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.67
     åren
    -0.66
    routeProvider
    -0.61
     useRouter
    -0.60
     springfox
    -0.55
     intStringLen
    -0.54
     WAP
    -0.54
     الرياضيه
    -0.53
    WireFormatLite
    -0.51
     lloc
    -0.51
    POSITIVE LOGITS
    CrossRef
    0.70
    Viitteet
    0.69
     fuel
    0.65
    __':
    0.64
    __":
    0.57
    )))));
    0.56
     Fuel
    0.56
     blight
    0.56
    tanooga
    0.55
    rium
    0.55
    Activations Density 2.588%

    No Known Activations