© 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. 27-GEMMASCOPE-RES-16K
    11. 8834
    Prev
    Next
    INDEX
    Explanations

    names and titles related to individuals, organizations, and established entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.54
     estekak
    -0.53
    BeginContext
    -0.48
    __(/*!
    -0.48
    Portail
    -0.46
    ContentAlignment
    -0.46
     Meksiku
    -0.45
    bkz
    -0.44
     мәкал
    -0.43
     vul
    -0.43
    POSITIVE LOGITS
     zelve
    0.43
    .”—
    0.40
     cremallera
    0.38
    ฯ
    0.38
     själva
    0.38
     totiž
    0.38
     harian
    0.38
     cuchar
    0.37
     kasarigan
    0.37
     gră
    0.36
    Activations Density 1.520%

    No Known Activations