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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53029
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals, particularly in entertainment or popular culture

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

    producer, page, attribute, net, lightning, community, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })`
    -1.01
    .")]
    -0.95
    ")){
    
    -0.91
    ."]
    -0.91
    >`;
    -0.91
    .")
    
    -0.90
    .",
    
    -0.87
    __':
    
    -0.86
    ".
    
    -0.86
    $")
    -0.86
    POSITIVE LOGITS
    !
    1.15
    !!!
    1.09
    !!
    1.05
    !!!!
    0.99
    !!!!!
    0.95
     damn
    0.91
    ?!
    0.90
    !!!!!!
    0.88
     ftw
    0.84
    !!!!!!!
    0.83
    Activations Density 0.142%

    No Known Activations