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. 5-GEMMASCOPE-RES-16K
    6. 10243
    Prev
    Next
    INDEX
    Explanations

    references to figures and supplementary materials in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.71
     stuff
    -0.66
    tamment
    -0.61
     Frost
    -0.60
    skal
    -0.58
    ⓧ
    -0.57
    vast
    -0.56
     Fro
    -0.55
    <>("
    -0.53
    InkWell
    -0.53
    POSITIVE LOGITS
    Figure
    1.62
     Figure
    1.37
    Fig
    1.20
     Fig
    1.03
    Table
    0.93
     Table
    0.85
     Figura
    0.81
    sizeCache
    0.80
    Рис
    0.80
    如图
    0.80
    Activations Density 0.274%

    No Known Activations