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. 12850
    Prev
    Next
    INDEX
    Explanations

    programming and markup language syntax 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
    siąż
    -0.46
    خواندن
    -0.45
     Strategy
    -0.44
    KeySpec
    -0.42
     Profil
    -0.41
    ologous
    -0.41
    JsonPropertyName
    -0.40
     TECHNIQUE
    -0.40
     conhece
    -0.40
    Viki
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    0.77
     Latex
    0.76
     intptr
    0.76
     utafitiHapana
    0.74
    TeX
    0.73
     Paglinawan
    0.71
     LAT
    0.71
     LaTeX
    0.70
     latex
    0.69
    LookAnd
    0.69
    Activations Density 0.613%

    No Known Activations