Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3992
    Prev
    Next
    INDEX
    Explanations

    variations of the letter 'y'

    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
    ')")
    -0.91
    "");
    -0.88
    %");
    -0.87
    )");
    
    -0.83
    ."));
    -0.82
     Inſ
    -0.81
    ","");
    -0.79
    !».
    -0.79
    )]);
    -0.79
     purpoſe
    -0.78
    POSITIVE LOGITS
     Y
    1.93
     y
    1.69
    Y
    1.64
     getY
    1.23
     Yel
    1.20
     Yag
    1.17
    y
    1.09
    getY
    1.09
     yachts
    1.09
     yacht
    1.08
    Activations Density 0.085%

    No Known Activations