© 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. 5-GEMMASCOPE-RES-16K
    11. 5333
    Prev
    Next
    INDEX
    Explanations

    references to various time periods, particularly those related to years and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.66
     is
    -0.56
    iformis
    -0.52
     =
    -0.52
     lisää
    -0.48
     more
    -0.46
    zwungen
    -0.45
    gez
    -0.45
     rius
    -0.45
    tris
    -0.45
    POSITIVE LOGITS
     pleaſure
    0.92
     Efq
    0.87
    )";
    0.87
    ,:);
    0.85
    .")
    0.83
     faſt
    0.83
     houſe
    0.82
    ".
    0.82
    脚注の使い方
    0.81
     ſmall
    0.80
    Activations Density 0.125%

    No Known Activations