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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 15660
    Prev
    Next
    INDEX
    Explanations

    phrases related to enjoyment and positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ine
    -0.75
    B
    -0.65
    Al
    -0.64
     B
    -0.63
    الت
    -0.63
    Le
    -0.63
     Al
    -0.60
    les
    -0.60
    Het
    -0.59
    um
    -0.59
    POSITIVE LOGITS
    enjoy
    1.54
     enjoyment
    1.53
     Enjoy
    1.41
     ENJOY
    1.39
     enjoy
    1.35
     enjoyed
    1.35
    Enjoying
    1.32
     pleaſure
    1.31
    Enjoyed
    1.28
    ENJOY
    1.27
    Activations Density 0.040%

    No Known Activations