© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 690
    Prev
    Next
    INDEX
    Explanations

    references to component elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.76
     '+':
    -0.67
    __':
    -0.64
    __":
    -0.58
    voerd
    -0.55
    horabuena
    -0.54
    ("}");
    -0.53
     estimés
    -0.53
    /$',
    -0.52
     '</
    -0.51
    POSITIVE LOGITS
     ElementRef
    0.75
    OGND
    0.65
     intptr
    0.63
    原始内容存档于
    0.62
    μερα
    0.61
    key
    0.59
    jsii
    0.57
    feira
    0.55
    存于互联网档案馆
    0.54
    ImageContext
    0.53
    Activations Density 0.034%

    No Known Activations