© 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. 16-GEMMASCOPE-RES-16K
    11. 11398
    Prev
    Next
    INDEX
    Explanations

    various configurations of materials and coatings in descriptions

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

    Comes after prepositions "with," "of," or "in."

    np_acts-logits-general · gemini-2.0-flash

    coating materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     riuscito
    -0.48
     Sociales
    -0.45
    ’
    -0.43
     уж
    -0.43
    での
    -0.43
    之
    -0.42
     Ouv
    -0.39
     idee
    -0.39
     ύ
    -0.39
    stoj
    -0.39
    POSITIVE LOGITS
     ModelExpression
    1.04
    WriteTagHelper
    0.93
    RegistryLite
    0.86
    Hentet
    0.84
    aarrggbb
    0.83
    SerializedName
    0.77
    niająca
    0.76
    InjectAttribute
    0.74
    AdapterFactory
    0.74
    enterOuterAlt
    0.73
    Activations Density 0.612%

    No Known Activations