© 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. 28-GEMMASCOPE-RES-16K
    11. 4792
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific advancements and concepts

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

    Follows "who," "the," or "have."

    np_acts-logits-general · gemini-2.0-flash

    people who have created something

    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
    HideFlags
    -0.45
     quæ
    -0.38
    tencent
    -0.36
     stand
    -0.36
    ]=>
    -0.36
    uxxxx
    -0.35
     house
    -0.34
     bench
    -0.33
     trời
    -0.32
    layoutControl
    -0.32
    POSITIVE LOGITS
    tvguidetime
    0.61
    entrevista
    0.57
     vibrating
    0.57
     interesados
    0.56
     jagged
    0.55
     curled
    0.53
    ftagPool
    0.53
    لينكات
    0.53
     débat
    0.52
    RegressionTest
    0.52
    Activations Density 1.565%

    No Known Activations