© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5350
    Prev
    Next
    INDEX
    Explanations

    references to television and TV shows

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

    "TV" or "Television"

    np_acts-logits-general · gemini-2.0-flash

    TV shows and related media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )$/,
    -0.81
     Salta
    -0.71
     })}
    -0.68
    ]))
    
    -0.67
    }';
    -0.66
    ]),
    
    -0.66
    ]));
    
    -0.64
    nnnn
    -0.64
    %;">
    -0.61
    }));
    
    -0.61
    POSITIVE LOGITS
     TV
    1.25
     television
    1.19
     TVs
    1.11
     tv
    1.10
     Television
    1.08
     televisions
    1.06
    television
    1.02
    Television
    0.99
     Tv
    0.98
    TV
    0.94
    Activations Density 0.077%

    No Known Activations