© 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. 13-GEMMASCOPE-RES-16K
    6. 6836
    Prev
    Next
    INDEX
    Explanations

    terms related to filtration and purification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBAction
    -0.38
    PAIGN
    -0.37
    Embrace
    -0.36
     marea
    -0.36
     watched
    -0.35
    никюр
    -0.34
     Embrace
    -0.34
    kształ
    -0.34
    bakar
    -0.33
     excitation
    -0.33
    POSITIVE LOGITS
     filtration
    0.81
    featureID
    0.75
     filtering
    0.69
     autorytatywna
    0.68
    filtration
    0.68
     Filtration
    0.67
     resourceCulture
    0.67
     filter
    0.65
     filtra
    0.61
     ujednoznacz
    0.61
    Activations Density 0.981%

    No Known Activations