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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12761
    Prev
    Next
    INDEX
    Explanations

    words related to cancer biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.77
    RegressionTest
    -0.76
     validamos
    -0.73
    psum
    -0.69
    DrawerToggle
    -0.68
     disambiguazione
    -0.67
    interopRequire
    -0.67
     AssemblyTitle
    -0.67
    XmlAccessorType
    -0.66
    bital
    -0.66
    POSITIVE LOGITS
     wier
    0.69
    ua
    0.69
    ias
    0.57
     IAA
    0.57
     Rie
    0.56
    ue
    0.56
    uez
    0.56
    Iain
    0.55
     Iain
    0.54
    uo
    0.53
    Activations Density 0.650%

    No Known Activations