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. 13378
    Prev
    Next
    INDEX
    Explanations

    topics related to cancer treatment and biological mechanisms in cellular processes

    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
    eder
    -0.49
    SPATH
    -0.48
    odenal
    -0.47
     Arkivert
    -0.47
    SEB
    -0.46
    ritch
    -0.46
    hoga
    -0.46
    iecie
    -0.46
    SequentialGroup
    -0.46
    TabLayout
    -0.45
    POSITIVE LOGITS
     plays
    2.67
     play
    2.56
     played
    2.50
     Plays
    2.31
     playing
    2.23
    plays
    2.23
    play
    2.19
    Play
    2.12
     Play
    2.09
     PLAY
    2.07
    Activations Density 1.015%

    No Known Activations