© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1205
    Prev
    Next
    INDEX
    Explanations

    incidents or issues related to infrastructure and service disruptions

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

    Temporary shutdowns, disruptions, or service outages

    np_acts-logits-general · gemini-2.0-flash

    temporary shutdown or suspension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.57
    AndEndTag
    -0.47
     ejer
    -0.39
    ReusableCell
    -0.38
    */].
    -0.34
    basicConfig
    -0.33
     reproducción
    -0.33
    OGND
    -0.32
     seseorang
    -0.32
     soddis
    -0.32
    POSITIVE LOGITS
     temporarily
    0.96
     shutdown
    0.80
     suspend
    0.76
    tempor
    0.76
     temporary
    0.76
     suspending
    0.76
     shut
    0.73
     suspension
    0.73
     closed
    0.71
     shutting
    0.70
    Activations Density 0.249%

    No Known Activations