© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9211
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" and related structural components in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.77
    parsedMessage
    -0.67
    bewerken
    -0.64
    justed
    -0.60
     autorytatywna
    -0.60
     समीक्षाओं
    -0.59
    StructEnd
    -0.59
    principalTable
    -0.59
     تضيفلها
    -0.59
    ätigkeit
    -0.59
    POSITIVE LOGITS
    +:+
    0.53
    ItemGroup
    0.46
    不住
    0.46
    openConnection
    0.46
    Traceback
    0.45
    rai
    0.44
    LElement
    0.43
     Ferdinando
    0.43
    さんと
    0.43
    WriteTagHelper
    0.42
    Activations Density 0.382%

    No Known Activations