© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9508
    Prev
    Next
    INDEX
    Explanations

    references to medical treatments and protocols related to eye conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quelize
    -0.84
     DriverManager
    -0.82
     TableColumn
    -0.81
     وتسجيلات
    -0.78
     sequelize
    -0.76
    skrä
    -0.75
    aarrggbb
    -0.73
     مُعرِّف
    -0.73
    //
    -0.72
    Referensi
    -0.70
    POSITIVE LOGITS
    ting
    1.11
    tttt
    1.05
    ttt
    1.04
    thet
    1.02
    tt
    0.96
    tet
    0.91
    tait
    0.86
    lit
    0.84
    Mait
    0.84
    tott
    0.84
    Activations Density 3.034%

    No Known Activations