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. 17-GEMMASCOPE-RES-65K
    6. 28478
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or topics in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ''')
    -1.00
    ."</
    -0.93
    </h2>
    -0.92
    ")){
    
    -0.92
    }*/
    
    -0.90
    ']?>
    -0.89
    ')")
    -0.88
    '))
    
    -0.88
    ']],
    -0.87
    ]]
    
    -0.85
    POSITIVE LOGITS
    <blockquote>
    1.10
    <strong>
    0.98
    <b>
    0.88
    <em>
    0.82
    <code>
    0.82
     brancas
    0.76
     anledning
    0.74
    <i>
    0.69
    #######
    0.66
     linings
    0.66
    Activations Density 0.002%

    No Known Activations