© 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. 2-GEMMASCOPE-RES-16K
    11. 8346
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of "series" and "veteran," particularly in contexts involving experiences or specific characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.64
    jewództ
    -0.48
    Enllaços
    -0.44
     πως
    -0.44
     architet
    -0.43
     shears
    -0.42
     protoimpl
    -0.42
     surla
    -0.42
    Ligações
    -0.42
     intervention
    -0.41
    POSITIVE LOGITS
     series
    0.79
     indicate
    0.75
     indicates
    0.73
     already
    0.71
    already
    0.70
     indicating
    0.69
     veteran
    0.67
    indicate
    0.67
     Already
    0.67
    Already
    0.67
    Activations Density 0.098%

    No Known Activations