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 - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 1299
    Prev
    Next
    INDEX
    Explanations

    references to the atmosphere or atmospheric conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.78
    ])
    
    -0.77
    ]))
    
    -0.73
    '))
    
    -0.73
    ⮕
    -0.71
    cherichia
    -0.71
    ]);
    
    -0.70
    VolleyError
    -0.67
    ));
    
    -0.66
    ({
    
    -0.66
    POSITIVE LOGITS
     atmosphere
    1.88
     Atmosphere
    1.71
    atmosphere
    1.67
     atmospheres
    1.66
    Atmosphere
    1.57
     atmos
    1.46
     Atmos
    1.40
    Atmos
    1.38
     atmospheric
    1.37
     Atmosphäre
    1.33
    Activations Density 0.056%

    No Known Activations