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. 20-GEMMASCOPE-RES-16K
    6. 12851
    Prev
    Next
    INDEX
    Explanations

    a variety of structured data formats and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cy
    -0.47
    SpringRunner
    -0.43
    ({},
    -0.43
     necessari
    -0.41
    뿐
    -0.40
    +.
    -0.40
    chy
    -0.39
    ouk
    -0.39
    ita
    -0.39
    ierenden
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.91
    MLLoader
    0.87
     ProtoMessage
    0.85
    tagHelperRunner
    0.81
     saites
    0.77
     Normdatei
    0.70
     विश्वसनीयता
    0.69
     المعيارى
    0.68
    #
    0.67
    principalColumn
    0.67
    Activations Density 0.130%

    No Known Activations