Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13445
    Prev
    Next
    INDEX
    Explanations

    descriptions of paths and trails

    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
     كومونز
    -0.58
    contentLoaded
    -0.53
    MigrationBuilder
    -0.53
     oprot
    -0.52
    tvguidetime
    -0.51
     Motel
    -0.51
     negócio
    -0.50
    protoimpl
    -0.50
    脚注の使い方
    -0.50
    ScopeManager
    -0.50
    POSITIVE LOGITS
     parks
    1.64
     park
    1.60
    parks
    1.28
     Parks
    1.26
    park
    1.20
    Parks
    1.18
     parques
    1.11
     playgrounds
    1.07
     recreation
    1.05
     parque
    1.03
    Activations Density 0.217%

    No Known Activations