© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4740
    Prev
    Next
    INDEX
    Explanations

    instances of the word "se" in various contexts

    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
    Microkernel
    -0.44
     segregation
    -0.43
     Specifically
    -0.43
     Segment
    -0.42
    缘
    -0.41
    緣
    -0.40
     Se
    -0.40
    Specifically
    -0.40
     segment
    -0.40
    ManagedBean
    -0.40
    POSITIVE LOGITS
    se
    2.59
    SE
    1.45
    semen
    0.82
    sew
    0.71
    ses
    0.69
    sega
    0.68
    sef
    0.68
    seb
    0.66
    sej
    0.65
    seid
    0.65
    Activations Density 0.348%

    No Known Activations