© 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. 28-GEMMASCOPE-RES-16K
    11. 5555
    Prev
    Next
    INDEX
    Explanations

    terms related to semi-parametric statistical methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "Semi" or "Sem"

    np_acts-logits-general · gemini-2.0-flash

    words beginning with semi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.39
     cardiaque
    -0.37
     getattr
    -0.37
     Winaray
    -0.35
    orologio
    -0.35
    HasIndex
    -0.35
    dicos
    -0.34
    lankton
    -0.33
     pylori
    -0.33
    :^(
    -0.33
    POSITIVE LOGITS
     Sem
    0.95
     Semi
    0.93
    Sem
    0.92
     sem
    0.90
     semi
    0.84
     SEM
    0.84
    Semi
    0.81
    SEM
    0.79
    sem
    0.79
     SEMI
    0.78
    Activations Density 0.159%

    No Known Activations