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. 319
    Prev
    Next
    INDEX
    Explanations

    terms related to software assemblies and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code comments and annotations related to software licensing and documentation.

    oai_token-act-pair · gpt-4oTriggered by @timna
    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
    FormTagHelper
    -0.80
     Италијани
    -0.76
    oredCriteria
    -0.71
    Życiorys
    -0.70
    richTextPanel
    -0.69
     <<<<<<<<<<<<<<
    -0.66
     بيها
    -0.65
    Jîn
    -0.64
     تضيفلها
    -0.64
    AutoField
    -0.64
    POSITIVE LOGITS
    migrationBuilder
    0.48
    ward
    0.47
     disk
    0.45
     Drapeau
    0.44
    omsday
    0.44
     الحره
    0.44
     pés
    0.42
     délic
    0.42
    勉
    0.42
    ╔
    0.41
    Activations Density 0.094%

    No Known Activations