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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2818
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "magic."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.52
    posedge
    -0.47
     doInBackground
    -0.45
    HomeAsUpEnabled
    -0.43
    ței
    -0.43
    dstuk
    -0.42
    StackNavigator
    -0.41
    faßt
    -0.41
     utafitiHapana
    -0.41
     atteinte
    -0.41
    POSITIVE LOGITS
     Magic
    0.75
    Magic
    0.73
     magic
    0.71
    magic
    0.69
    coffee
    0.56
     MAGIC
    0.54
     coffee
    0.52
    blue
    0.51
     blue
    0.50
     Coffee
    0.50
    Activations Density 0.153%

    No Known Activations