© 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. 3684
    Prev
    Next
    INDEX
    Explanations

    points indicating a significant change or condition

    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
     ProtoMessage
    -0.75
    exitRule
    -0.73
     AppColors
    -0.73
    YourGuide
    -0.72
     StringTokenizer
    -0.71
    jsonwebtoken
    -0.69
     <=",
    -0.69
     विश्वसनीयता
    -0.68
     Hiram
    -0.67
    DoubleQuotes
    -0.67
    POSITIVE LOGITS
    致
    0.57
    จน
    0.52
     causing
    0.51
    导致
    0.46
     îng
    0.46
    gerät
    0.45
     致
    0.44
    導致
    0.43
    IonicModule
    0.43
     that
    0.42
    Activations Density 0.353%

    No Known Activations