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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]))
    
    -1.16
    ")));
    
    -0.93
    PerformLayout
    -0.92
    ]));
    
    -0.91
     незавершена
    -0.90
    ]")]
    -0.90
     }));
    -0.88
    ]),
    
    -0.88
    )))
    
    -0.87
     متعلقه
    -0.86
    POSITIVE LOGITS
     Party
    1.70
     party
    1.69
     PARTY
    1.60
    PARTY
    1.55
    Party
    1.53
    party
    1.48
     parties
    1.40
     Parties
    1.35
    Parties
    1.24
     PARTIES
    1.19
    Activations Density 0.026%

    No Known Activations