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. 18-GEMMASCOPE-RES-16K
    6. 10169
    Prev
    Next
    INDEX
    Explanations

    technical and industry-related terms, particularly in the field of computing and data centers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     user
    -0.47
     sear
    -0.45
     Lucas
    -0.45
     naveg
    -0.43
     web
    -0.43
    न्त
    -0.41
     User
    -0.40
    getUserId
    -0.40
    ForUser
    -0.40
    ToScroll
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    0.91
    XmlAccessType
    0.82
    HostException
    0.77
     datac
    0.74
     BoxDecoration
    0.73
    posedge
    0.73
    IUrlHelper
    0.69
    AutoScale
    0.69
    IndentedString
    0.69
     virtualization
    0.68
    Activations Density 0.483%

    No Known Activations