© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9654
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their spacing, particularly brackets and brackets with specific conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.47
    Portale
    -0.45
    ↵↵
    -0.41
    side
    -0.39
     Side
    -0.37
    淬
    -0.37
    òn
    -0.37
      
    -0.36
     Bottom
    -0.36
    Channel
    -0.36
    POSITIVE LOGITS
    ]
    2.86
    ]
    2.70
    ?]
    2.63
    .]
    2.59
    !]
    2.56
    ].
    2.55
    ]</
    2.53
     ]
    2.44
    ],
    2.42
    ]:
    2.41
    Activations Density 0.318%

    No Known Activations