© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13317
    Prev
    Next
    INDEX
    Explanations

    terms related to medical processes and anatomical locations

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

    "of the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DBNull
    -0.84
     propOrder
    -0.76
     يتيمه
    -0.70
    SourceChecksum
    -0.69
    tagHelperRunner
    -0.66
    AxisAlignment
    -0.65
    awaiter
    -0.65
    requestCode
    -0.63
     Réponses
    -0.62
    ]-->
    -0.61
    POSITIVE LOGITS
    脚注の使い方
    0.51
     suatu
    0.50
     espesor
    0.50
     chaque
    0.45
     '{@
    0.43
    さて
    0.42
    mmu
    0.42
    uiente
    0.42
    travis
    0.41
    Referencies
    0.41
    Activations Density 0.707%

    No Known Activations