© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1039
    Prev
    Next
    INDEX
    Explanations

    references to specific diagnostic tests and viruses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.61
     Sme
    -0.57
     Reſ
    -0.56
     ſch
    -0.55
     invokingState
    -0.54
     compét
    -0.53
     Shaksp
    -0.53
     ſen
    -0.53
    jähriger
    -0.52
     للش
    -0.51
    POSITIVE LOGITS
     nahilalakip
    0.89
    RegressionTest
    0.68
     كمان
    0.65
     հղումներ
    0.65
    ptonshire
    0.63
    toMatchSnapshot
    0.63
     AssemblyProduct
    0.63
     initComponents
    0.56
     kaarangay
    0.56
    InsertCommand
    0.56
    Activations Density 3.091%

    No Known Activations