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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 2788
    Prev
    Next
    INDEX
    Explanations

    topics related to academic studies and their evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Према
    -0.54
    volmente
    -0.46
     ),
    
    -0.45
    zan
    -0.44
    noinspection
    -0.43
    '),
    
    -0.43
     });
    
    -0.42
    ()],
    -0.41
    `;
    
    -0.41
    ],
    
    -0.41
    POSITIVE LOGITS
    ]--;
    0.79
    twimg
    0.77
    Personensuche
    0.76
    SequentialGroup
    0.75
    thâu
    0.75
    hnia
    0.73
    RegistryLite
    0.72
    AndroidJUnit
    0.72
    complexContent
    0.71
    itattu
    0.71
    Activations Density 0.689%

    No Known Activations