© 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. 4-GEMMASCOPE-RES-16K
    11. 11589
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds in a scientific context, particularly those involving chromium, germanium, and tellurium

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.75
    Personendaten
    -0.71
     ujednoznacz
    -0.68
    SourceChecksum
    -0.68
     Sixt
    -0.67
     quæ
    -0.64
    tagHelperRunner
    -0.64
     resourceCulture
    -0.64
    +#+#
    -0.64
    paramref
    -0.64
    POSITIVE LOGITS
    posia
    0.47
    >-->
    0.46
    ViewFeatures
    0.45
    TabStop
    0.40
     c
    0.39
    meliharaan
    0.39
    表
    0.39
     inter
    0.39
     eins
    0.38
    border
    0.37
    Activations Density 2.253%

    No Known Activations