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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11035
    Prev
    Next
    INDEX
    Explanations

    closing brackets and semicolons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    談社
    -0.75
     Lovel
    -0.73
     Shand
    -0.71
     Vivian
    -0.71
    Spoljašnje
    -0.69
    Jax
    -0.69
     Lindsey
    -0.66
     Jacinto
    -0.66
     hark
    -0.64
     Spie
    -0.64
    POSITIVE LOGITS
    ];
    1.27
    ];
    
    1.14
    ()];
    0.99
     ];
    0.97
    }];
    0.94
    __":
    
    0.93
    )];
    0.91
    ]];
    0.91
     @"/
    0.89
    _;
    0.88
    Activations Density 0.079%

    No Known Activations