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. 1239
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and the beginning of sentences

    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
     ')
    
    -0.56
     ")");
    -0.56
     skjø
    -0.54
    ]))
    
    -0.54
     ")
    
    -0.52
    }]
    
    -0.52
    kjø
    -0.52
    ])))
    -0.51
    ++)
    
    -0.51
     strøm
    -0.50
    POSITIVE LOGITS
     Мексичка
    0.86
    Personensuche
    0.85
    //
    0.81
    RunWith
    0.77
    .$,
    0.77
    Geplaatst
    0.77
    /*
    0.74
    ItemBackground
    0.69
    MigrationBuilder
    0.68
    °,
    0.67
    Activations Density 0.915%

    No Known Activations