Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8393
    Prev
    Next
    INDEX
    Explanations

    code comments in the document

    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
     للمعارف
    -0.71
     ब्रेकडाउन
    -0.63
    RegressionTest
    -0.62
    دانشنامهٔ
    -0.62
    Autoritní
    -0.62
    StoryboardSegue
    -0.61
    GOTREF
    -0.60
    parsedMessage
    -0.58
    хьтан
    -0.55
     صوتيه
    -0.54
    POSITIVE LOGITS
     Universitäts
    0.41
    binaan
    0.36
     yapı
    0.34
    ulihan
    0.34
     Cabral
    0.33
    belajaran
    0.33
     présidentielle
    0.33
    ambilan
    0.33
     Rücken
    0.32
     oeil
    0.32
    Activations Density 0.339%

    No Known Activations