© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6501
    Prev
    Next
    INDEX
    Explanations

    specific references to the letter 'L' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.92
    eſ
    -0.91
    }}]{
    -0.82
    )");
    -0.80
    )";
    -0.79
    BibitemShut
    -0.79
     raiſ
    -0.78
     ſhall
    -0.78
     myſelf
    -0.77
     فريبيس
    -0.77
    POSITIVE LOGITS
    L
    2.80
     L
    1.73
    Ls
    1.30
    getL
    1.26
    Ｌ
    1.03
    l
    1.00
    M
    0.96
    R
    0.93
    T
    0.92
    𝐿
    0.91
    Activations Density 0.119%

    No Known Activations