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. 11810
    Prev
    Next
    INDEX
    Explanations

    attributes related to simplicity, durability, and cost-effectiveness in products or processes

    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
    AndEndTag
    -0.88
    BagLayout
    -0.85
     noDo
    -0.77
    AccessorTable
    -0.77
     doubtnut
    -0.73
    mybatisplus
    -0.72
     ligiloj
    -0.72
     CreateTagHelper
    -0.68
     Efq
    -0.67
    getKeyCode
    -0.66
    POSITIVE LOGITS
     and
    0.63
     easy
    0.60
     convenient
    0.56
    だれ
    0.56
    ченной
    0.55
    raborty
    0.55
    ्यों
    0.53
     Convenient
    0.52
     easily
    0.51
     mudah
    0.50
    Activations Density 0.179%

    No Known Activations