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. 13-GEMMASCOPE-RES-16K
    6. 256
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and elements related to data structures or types

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

    mathematical symbols, code-related punctuation, and notation used in programming and technical contexts.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CWE
    -0.56
     fields
    -0.54
    DJANGO
    -0.52
    wiad
    -0.50
     ring
    -0.49
    ::_('
    -0.49
    Удачи
    -0.49
    ideration
    -0.48
    ắn
    -0.48
    gment
    -0.47
    POSITIVE LOGITS
    الإنجليزية
    0.65
    InjectAttribute
    0.62
    TargetException
    0.60
     snippetHide
    0.60
    EndInit
    0.55
     tandis
    0.51
     PartialEq
    0.51
    ExtendWith
    0.50
     Superhost
    0.50
    numerusform
    0.48
    Activations Density 0.459%

    No Known Activations