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. 1-GEMMASCOPE-RES-16K
    6. 6870
    Prev
    Next
    INDEX
    Explanations

    references to patches in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    };*/
    -0.72
    ]));
    
    -0.70
    addCriterion
    -0.67
    "]));
    -0.66
    }}</
    -0.66
    Cyfeiriadau
    -0.66
    fromnode
    -0.65
     réguli
    -0.64
    )));
    
    -0.64
     gagal
    -0.64
    POSITIVE LOGITS
     patch
    1.64
     Patch
    1.50
    patch
    1.42
    Patch
    1.37
     patches
    1.31
     PATCH
    1.17
    PATCH
    1.08
    patches
    1.06
     patched
    1.05
     Patches
    1.04
    Activations Density 0.067%

    No Known Activations