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 - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6375
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in code, particularly focusing on parentheses, brackets, and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]),
    
    -0.94
    ])),
    -0.90
    ]));
    -0.89
    RectangleBorder
    -0.88
     ostavi
    -0.86
    },[
    -0.85
    ])):
    -0.85
    ']),
    -0.85
    )),
    
    -0.84
    })),
    -0.84
    POSITIVE LOGITS
    shund
    0.61
    [toxicity=0]
    0.61
    +#+#
    0.58
    s
    0.56
     colspan
    0.56
    #{
    0.54
    WRENCE
    0.53
    sequelize
    0.53
     effectivement
    0.53
    webdriver
    0.51
    Activations Density 0.490%

    No Known Activations