© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3688
    Prev
    Next
    INDEX
    Explanations

    references to content and file structure within code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ธ์
    -0.47
     grunn
    -0.46
    going
    -0.44
    ύ
    -0.42
    thol
    -0.41
     rekening
    -0.41
    ἶ
    -0.40
     clé
    -0.39
     thư
    -0.39
     دف
    -0.39
    POSITIVE LOGITS
     المعيارى
    0.91
    ValueStyle
    0.91
    évaluateur
    0.90
    TagMode
    0.88
    AnchorTagHelper
    0.83
    تقاوى
    0.80
    InitVars
    0.77
     disambiguazione
    0.75
     AssemblyTitle
    0.74
    res
    0.70
    Activations Density 0.072%

    No Known Activations