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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15542
    Prev
    Next
    INDEX
    Explanations

    references to comedians and their works

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

    comedy and comedians

    np_acts-logits-general · gemini-2.0-flash

    jokes and comedians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.53
    MessageOf
    -0.47
     CreateTagHelper
    -0.45
     OST
    -0.41
    rätt
    -0.41
    NameValuePair
    -0.41
     Gli
    -0.41
    rungsseite
    -0.40
    Parcelize
    -0.40
     insuffisamment
    -0.40
    POSITIVE LOGITS
     comedy
    1.33
     comedians
    1.21
     comedian
    1.19
     Comedy
    1.15
    comedy
    1.14
    Comedy
    1.11
     comedic
    1.07
     jokes
    0.92
     comedia
    0.92
     humor
    0.85
    Activations Density 0.066%

    No Known Activations