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. 14222
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to procedures and properties of biological materials

    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
    fromnode
    -0.70
     Efq
    -0.57
     кӀ
    -0.57
    AnchorStyles
    -0.56
    CppCodeGen
    -0.56
    InSection
    -0.55
     لينك
    -0.55
    extAlignment
    -0.55
    FieldBuilder
    -0.53
     defaultstate
    -0.50
    POSITIVE LOGITS
     makes
    1.52
    makes
    1.26
     membuatnya
    1.19
     Makes
    1.19
     make
    1.18
    Makes
    1.17
    使得
    1.17
     means
    1.16
     ensures
    1.14
    使其
    1.07
    Activations Density 0.682%

    No Known Activations