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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 318
    Prev
    Next
    INDEX
    Explanations

    instances of new beginnings or introductions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning of text blocks or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    up
    -0.48
    lo
    -0.47
    ND
    -0.47
    rom
    -0.46
    ers
    -0.46
    ритори
    -0.45
    Père
    -0.45
    setView
    -0.45
    FieldDescriptor
    -0.43
    వే
    -0.43
    POSITIVE LOGITS
    )))),
    1.30
    )))
    
    1.01
    ]))
    
    0.99
    ")));
    
    0.96
    }))
    
    0.94
    )))));
    0.93
    '):
    
    0.89
    }),
    
    0.88
    "],
    
    0.88
    )),
    
    0.85
    Activations Density 0.003%

    No Known Activations