© 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. 25-GEMMASCOPE-RES-16K
    6. 10716
    Prev
    Next
    INDEX
    Explanations

    structured data format elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OLUTION
    -0.48
    bolistas
    -0.47
     Ato
    -0.47
    hnia
    -0.46
     kiệm
    -0.45
    umbus
    -0.45
    dette
    -0.44
    ividual
    -0.44
    árol
    -0.44
     pick
    -0.44
    POSITIVE LOGITS
    ];
    
    0.92
    );
    
    0.87
    ));
    
    0.86
    ]);
    
    0.86
    OGND
    0.82
    };
    
    0.79
    ))
    
    0.78
    ]
    
    0.77
    ),
    
    0.77
    ']);
    
    0.76
    Activations Density 1.396%

    No Known Activations