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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 5868
    Prev
    Next
    INDEX
    Explanations

    references to humor and satire in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.73
    ]-->
    -0.68
     snippetHide
    -0.63
    ]]
    
    -0.61
    ijiet
    -0.59
    Sprache
    -0.59
    didSet
    -0.58
     stanovnika
    -0.58
    zeczytaj
    -0.58
    };*/
    -0.57
    POSITIVE LOGITS
    bkz
    0.73
     glorious
    0.64
    нибудь
    0.64
     blah
    0.62
     annoying
    0.61
     hideous
    0.60
     hilarious
    0.60
     plastique
    0.60
    (!)
    0.58
     (!)
    0.58
    Activations Density 0.844%

    No Known Activations