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. 8057
    Prev
    Next
    INDEX
    Explanations

    dates and specific months in a text

    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
    TintMode
    -0.64
     MessageBoxIcon
    -0.58
     JAXBElement
    -0.53
    INSEE
    -0.52
     resourceCulture
    -0.51
    smithy
    -0.49
    cinfo
    -0.49
     verwijzen
    -0.49
    Pranala
    -0.48
     pasti
    -0.48
    POSITIVE LOGITS
     Oct
    2.85
     Aug
    2.80
    Oct
    2.78
    Aug
    2.65
     Nov
    2.61
     Jul
    2.58
    Nov
    2.54
    Jul
    2.46
     Sep
    2.43
     Sept
    2.36
    Activations Density 0.124%

    No Known Activations