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. 20-GEMMASCOPE-RES-16K
    6. 4835
    Prev
    Next
    INDEX
    Explanations

    elements related to childhood and play experiences

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

    following articles or prepositions

    np_acts-logits-general · gemini-2.0-flash

    cute animal characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puta
    -0.52
    ParallelGroup
    -0.51
     dataGridView
    -0.48
     layui
    -0.47
    FUCK
    -0.47
     vrouwen
    -0.46
     Knives
    -0.46
    Fucking
    -0.46
     Frauen
    -0.46
    gheny
    -0.45
    POSITIVE LOGITS
     mischievous
    0.87
     anthrop
    0.84
     adorable
    0.79
     furry
    0.76
     mischief
    0.76
     naughty
    0.75
     cute
    0.75
     adventures
    0.72
     cuddly
    0.71
     mascot
    0.70
    Activations Density 0.376%

    No Known Activations