© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8900
    Prev
    Next
    INDEX
    Explanations

    closing brackets or braces in structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SCSI
    -0.82
     Koro
    -0.77
     MessageType
    -0.74
     testCase
    -0.72
     bst
    -0.69
    úsqueda
    -0.69
     VIE
    -0.67
     Ashby
    -0.66
     peine
    -0.65
     Montague
    -0.65
    POSITIVE LOGITS
     }));
    1.72
     })
    1.72
     });
    1.63
     });
    1.58
     })
    1.51
     }</
    1.49
     },
    1.47
     };
    1.46
     };
    1.43
     }}</
    1.41
    Activations Density 0.113%

    No Known Activations