© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6262
    Prev
    Next
    INDEX
    Explanations

    references to coding examples and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     Савезне
    -0.42
    oa̍t
    -0.37
     thought
    -0.37
     Italijanski
    -0.35
    <tbody>
    -0.35
    “…”
    -0.34
    もちゃ
    -0.34
    #
    -0.33
     beginning
    -0.32
     أ
    -0.32
    POSITIVE LOGITS
    omiast
    0.92
    脚注の使い方
    0.92
     immerhin
    0.87
     hiszen
    0.87
    tamment
    0.86
     Zudem
    0.82
    middels
    0.80
    Warto
    0.79
     πως
    0.78
     esimerkiksi
    0.76
    Activations Density 0.179%

    No Known Activations