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. 582
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance metrics related to vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    imetry
    -0.59
    imetric
    -0.53
    ástico
    -0.52
    спонд
    -0.51
    guet
    -0.50
    ingway
    -0.50
    dike
    -0.49
    sivité
    -0.48
    writeField
    -0.48
     Palt
    -0.47
    POSITIVE LOGITS
     engines
    0.68
     powering
    0.67
     SqlCommand
    0.66
     engine
    0.62
    DeleteBehavior
    0.60
     powers
    0.60
    esModule
    0.59
    powers
    0.59
    fuels
    0.58
     crankshaft
    0.58
    Activations Density 0.187%

    No Known Activations