© 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. 21-GEMMASCOPE-RES-16K
    11. 13292
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical methods and data calibration in analytical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.92
    NameInMap
    -0.85
     nakalista
    -0.84
     resourceCulture
    -0.71
    webElementXpaths
    -0.71
     &___
    -0.67
    sizeCache
    -0.66
    AccessorTable
    -0.64
     صوتيه
    -0.61
     CanadaChoose
    -0.60
    POSITIVE LOGITS
     prior
    0.54
     preliminary
    0.39
     preliminar
    0.39
     beforehand
    0.37
     previous
    0.36
     habet
    0.36
     preceding
    0.36
     dulu
    0.35
    Prior
    0.35
     Prior
    0.34
    Activations Density 1.367%

    No Known Activations