© 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. 23-GEMMASCOPE-RES-16K
    11. 14899
    Prev
    Next
    INDEX
    Explanations

    references to traditional anniversary gifts and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     malheureux
    -0.49
     neus
    -0.45
     fictitious
    -0.45
    ToolStrip
    -0.44
    Geral
    -0.43
     bullshit
    -0.43
     }}\
    -0.42
    lask
    -0.42
    猥
    -0.42
    UKAN
    -0.42
    POSITIVE LOGITS
     Roskov
    0.85
     autorytatywna
    0.78
     caption
    0.76
     captioned
    0.76
     JpaRepository
    0.73
     propOrder
    0.71
     disambiguazione
    0.71
    脚注の使い方
    0.71
    sizeCache
    0.70
    URLException
    0.70
    Activations Density 0.101%

    No Known Activations