© 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. 15386
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological advancements and their applications 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
     Geſch
    -0.88
     ſein
    -0.85
     ſich
    -0.85
     myſelf
    -0.85
     beſch
    -0.84
     betweenstory
    -0.83
     laſſen
    -0.82
    MLLoader
    -0.82
     ſeine
    -0.81
     geſch
    -0.81
    POSITIVE LOGITS
     tom
    0.34
     so
    0.30
     Tom
    0.30
    Tom
    0.30
     Pri
    0.24
    <eos>
    0.24
     pri
    0.24
    o
    0.24
    where
    0.24
     [
    0.23
    Activations Density 2.234%

    No Known Activations