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. 12-GEMMASCOPE-RES-16K
    6. 1458
    Prev
    Next
    INDEX
    Explanations

    terminology related to mechanical components and engineering descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nthetic
    -0.52
    AnchorTagHelper
    -0.51
    MessageTagHelper
    -0.50
    alini
    -0.50
    DrawerToggle
    -0.48
     خارجية
    -0.47
     localObject
    -0.47
     fala
    -0.46
    nat
    -0.46
     Italiana
    -0.46
    POSITIVE LOGITS
     space
    0.83
     spaces
    0.76
     area
    0.74
     TextInputType
    0.72
    IsContent
    0.70
    cavity
    0.70
    InSection
    0.70
     cavity
    0.68
    space
    0.68
     room
    0.67
    Activations Density 0.538%

    No Known Activations