Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7796
    Prev
    Next
    INDEX
    Explanations

    references to North Carolina and related geographical or institutional indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ges
    -0.52
     collection
    -0.51
     Navig
    -0.50
     kast
    -0.49
    bere
    -0.49
     cep
    -0.49
    ket
    -0.48
    承
    -0.48
     neighboring
    -0.47
     distribution
    -0.47
    POSITIVE LOGITS
     auroit
    0.73
    expandindo
    0.58
     pouvoit
    0.58
     feroit
    0.58
    AddTagHelper
    0.57
    transQ
    0.57
     istrinya
    0.56
     Región
    0.55
     Grüsse
    0.54
     læng
    0.54
    Activations Density 0.239%

    No Known Activations