© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 7568
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to conferences and organized events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    event and conference announcements with dates and details.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     navideño
    -0.50
     férias
    -0.49
     navideña
    -0.46
     cebola
    -0.44
    AutoField
    -0.44
    Monthly
    -0.44
     Weihnachten
    -0.44
     vakantie
    -0.43
     semanal
    -0.43
     MONTHLY
    -0.43
    POSITIVE LOGITS
     panels
    0.80
     panel
    0.77
     sessions
    0.74
     keynote
    0.73
     Panel
    0.68
     plenary
    0.66
    Panels
    0.64
    sessions
    0.64
    Panel
    0.63
     breakout
    0.63
    Activations Density 0.180%

    No Known Activations