© 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. 10-GEMMASCOPE-RES-16K
    11. 15532
    Prev
    Next
    INDEX
    Explanations

    terms related to specific features, mechanisms, and qualities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.48
     المعيارى
    -0.46
    principalTable
    -0.44
    hoes
    -0.42
    RTEE
    -0.42
     jet
    -0.41
    الإنجليزية
    -0.41
     Pase
    -0.40
    InSection
    -0.40
    oneofs
    -0.40
    POSITIVE LOGITS
     features
    0.69
     modifications
    0.61
     Features
    0.60
     neler
    0.60
     dingen
    0.59
     things
    0.59
     limitations
    0.57
    things
    0.57
     changes
    0.55
     Modifications
    0.54
    Activations Density 1.990%

    No Known Activations