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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52973
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements in programming language context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    set methods in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.69
     oprot
    -0.63
     otomatig
    -0.60
    MessageOf
    -0.60
     محفوظة
    -0.60
    ArrowToggle
    -0.59
     Италијани
    -0.59
    StoreMessageInfo
    -0.59
     оригіналу
    -0.59
     newBuilder
    -0.59
    POSITIVE LOGITS
    Current
    0.44
    דש
    0.42
     tapaht
    0.40
     IDisposable
    0.40
    сет
    0.40
    oxone
    0.40
    tometer
    0.40
     पास
    0.40
    ťa
    0.40
    olu
    0.40
    Activations Density 0.034%

    No Known Activations