© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 5386
    Prev
    Next
    INDEX
    Explanations

    references to comedians and comedic influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.60
     мәкал
    -0.59
     oprot
    -0.58
    Identyfik
    -0.56
     Arque
    -0.54
    StructEnd
    -0.54
     صوتيه
    -0.53
    +#+
    -0.52
    Bronnen
    -0.51
     marea
    -0.50
    POSITIVE LOGITS
     comedy
    1.21
     comedians
    1.16
     Comedy
    1.16
    comedy
    1.05
    Comedy
    1.03
     comedian
    1.02
     stand
    0.99
     sketch
    0.97
     comedic
    0.96
     improv
    0.94
    Activations Density 0.243%

    No Known Activations