© 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. 38-GEMMASCOPE-RES-16K
    6. 10110
    Prev
    Next
    INDEX
    Explanations

    phrases related to JSON data handling and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     miniaturka
    -0.57
     torebka
    -0.56
     enfans
    -0.55
     koszulka
    -0.51
     kurtka
    -0.50
     forbindelse
    -0.49
     vandens
    -0.49
     bluzka
    -0.47
     Geſ
    -0.47
     kwiat
    -0.47
    POSITIVE LOGITS
    tvguidetime
    0.60
     transfieras
    0.53
     <<<<<<<<<<<<<<
    0.52
     utafitiHapana
    0.49
    GEBURTSDATUM
    0.47
    ьаж
    0.47
     linkovi
    0.45
    Whom
    0.45
     yyr
    0.43
    bitField
    0.42
    Activations Density 0.371%

    No Known Activations