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-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65767
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical notation and symbols, particularly in the context of equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.77
    ])));
    -0.59
    ])))
    -0.58
    ]]);
    -0.54
    }));
    
    -0.51
    }))
    
    -0.51
    ]")]
    -0.50
    )))),
    -0.48
    ]))
    
    -0.48
    ]){
    
    -0.48
    POSITIVE LOGITS
    ArgsConstructor
    0.57
    ReusableCell
    0.56
    interopRequire
    0.47
     contemporaine
    0.47
    enterOuterAlt
    0.46
    PerformLayout
    0.46
    tinyos
    0.45
     quelcon
    0.44
    Signature
    0.44
    PropertyChanging
    0.44
    Activations Density 0.620%

    No Known Activations