© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2564
    Prev
    Next
    INDEX
    Explanations

    terms related to value, significance, and deviations 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.48
    évêque
    -0.44
     campagnes
    -0.40
     homophobic
    -0.40
    annonce
    -0.40
     Jugendliche
    -0.39
     rospy
    -0.38
     phénomènes
    -0.38
     BeautifulSoup
    -0.38
     unsustainable
    -0.38
    POSITIVE LOGITS
     precious
    0.74
     Deviation
    0.73
    precious
    0.68
     deviation
    0.68
     Deb
    0.67
    Deviation
    0.66
     dedu
    0.64
     devi
    0.64
    Deb
    0.63
     receipts
    0.63
    Activations Density 0.344%

    No Known Activations