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. 134
    Prev
    Next
    INDEX
    Explanations

    coding-related structures and functions in programming languages

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

    phrases related to technical or programming contexts, often involving formatting, encoding, or computational operations.

    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
    featureID
    -0.68
    ItemBackground
    -0.67
    CONSIN
    -0.66
     '\\;'
    -0.66
     strerror
    -0.65
     scolaires
    -0.63
    zyż
    -0.62
    pausal
    -0.62
    DoubleQuotes
    -0.61
    ItemLayout
    -0.61
    POSITIVE LOGITS
    Portale
    0.74
    لينكات
    0.69
     Turner
    0.57
     kasarigan
    0.56
    verwijspagina
    0.53
    rana
    0.50
     Far
    0.50
    orkan
    0.50
     Wer
    0.50
     Bell
    0.49
    Activations Density 0.913%

    No Known Activations