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. 4-GEMMASCOPE-RES-16K
    6. 3379
    Prev
    Next
    INDEX
    Explanations

    references to plastic materials and bags

    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
    ="#"><
    -0.88
     }</
    -0.79
    ")]
    
    -0.78
    }*/
    
    -0.77
    ")));
    
    -0.77
    )");
    
    -0.77
     ***/
    -0.75
    ]));
    
    -0.74
    )\}$
    -0.73
     }}"></
    -0.73
    POSITIVE LOGITS
     plastic
    2.49
     Plastic
    2.47
    Plastic
    2.44
    plastic
    2.29
     PLASTIC
    2.20
     plastics
    2.04
     plastique
    1.93
     plastik
    1.84
     Plastics
    1.82
     Plastik
    1.70
    Activations Density 0.085%

    No Known Activations